Compare commits
5 Commits
cjy-oneapi
...
Trigger-Di
| Author | SHA1 | Date | |
|---|---|---|---|
| 45e3c725f9 | |||
| 7f603f189b | |||
| a821f21a23 | |||
| 34fe3e6aa5 | |||
|
79af79d471 |
8
.gitignore
vendored
8
.gitignore
vendored
@@ -1,7 +1,5 @@
|
||||
__pycache__
|
||||
GW150914
|
||||
GW150914-origin
|
||||
GW150914-mini
|
||||
docs
|
||||
*.tmp
|
||||
|
||||
GW150914*
|
||||
.codex
|
||||
docs/
|
||||
@@ -16,14 +16,12 @@ import numpy
|
||||
File_directory = "GW150914" ## output file directory
|
||||
Output_directory = "binary_output" ## binary data file directory
|
||||
## The file directory name should not be too long
|
||||
MPI_processes = 8 ## number of mpi processes used in the simulation
|
||||
MPI_processes = 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)
|
||||
CPU_Part = 1.0
|
||||
GPU_Part = 0.0
|
||||
Debug_NaN_Check = 0 ## enable NaN checks in compute_rhs_bssn: 0 (off) or 1 (on)
|
||||
|
||||
|
||||
#################################################
|
||||
|
||||
|
||||
@@ -1,233 +0,0 @@
|
||||
|
||||
#################################################
|
||||
##
|
||||
## This file provides the input parameters required for numerical relativity.
|
||||
## XIAOQU
|
||||
## 2024/03/19 --- 2025/09/14
|
||||
## Modified for GW150914-mini test case
|
||||
##
|
||||
#################################################
|
||||
|
||||
import numpy
|
||||
|
||||
#################################################
|
||||
|
||||
## Setting MPI processes and the output file directory
|
||||
|
||||
File_directory = "GW150914-mini" ## output file directory
|
||||
Output_directory = "binary_output" ## binary data file directory
|
||||
## The file directory name should not be too long
|
||||
MPI_processes = 4 ## number of mpi processes used in the simulation (Reduced for laptop)
|
||||
|
||||
GPU_Calculation = "no" ## Use GPU or not
|
||||
## (prefer "no" in the current version, because the GPU part may have bugs when integrated in this Python interface)
|
||||
CPU_Part = 1.0
|
||||
GPU_Part = 0.0
|
||||
|
||||
#################################################
|
||||
|
||||
|
||||
#################################################
|
||||
|
||||
## Setting the physical system and numerical method
|
||||
|
||||
Symmetry = "equatorial-symmetry" ## Symmetry of System: choose equatorial-symmetry、no-symmetry、octant-symmetry
|
||||
Equation_Class = "BSSN" ## Evolution Equation: choose "BSSN", "BSSN-EScalar", "BSSN-EM", "Z4C"
|
||||
## If "BSSN-EScalar" is chosen, it is necessary to set other parameters below
|
||||
Initial_Data_Method = "Ansorg-TwoPuncture" ## initial data method: choose "Ansorg-TwoPuncture", "Lousto-Analytical", "Cao-Analytical", "KerrSchild-Analytical"
|
||||
Time_Evolution_Method = "runge-kutta-45" ## time evolution method: choose "runge-kutta-45"
|
||||
Finite_Diffenence_Method = "4th-order" ## finite-difference method: choose "2nd-order", "4th-order", "6th-order", "8th-order"
|
||||
Debug_NaN_Check = 0 ## enable NaN checks in compute_rhs_bssn: 0 (off) or 1 (on)
|
||||
|
||||
#################################################
|
||||
|
||||
|
||||
#################################################
|
||||
|
||||
## Setting the time evolutionary information
|
||||
|
||||
Start_Evolution_Time = 0.0 ## start evolution time t0
|
||||
Final_Evolution_Time = 100.0 ## final evolution time t1 (Reduced for quick test)
|
||||
Check_Time = 10.0
|
||||
Dump_Time = 10.0 ## time inteval dT for dumping binary data
|
||||
D2_Dump_Time = 10.0 ## dump the ascii data for 2d surface after dT'
|
||||
Analysis_Time = 1.0 ## dump the puncture position and GW psi4 after dT"
|
||||
Evolution_Step_Number = 10000000 ## stop the calculation after the maximal step number
|
||||
Courant_Factor = 0.5 ## Courant Factor
|
||||
Dissipation = 0.15 ## Kreiss-Oliger Dissipation Strength
|
||||
|
||||
#################################################
|
||||
|
||||
|
||||
#################################################
|
||||
|
||||
## Setting the grid structure
|
||||
|
||||
basic_grid_set = "Patch" ## grid structure: choose "Patch" or "Shell-Patch"
|
||||
grid_center_set = "Cell" ## grid center: chose "Cell" or "Vertex"
|
||||
|
||||
grid_level = 7 ## total number of AMR grid levels (Reduced from 9)
|
||||
static_grid_level = 4 ## number of AMR static grid levels (Reduced from 5)
|
||||
moving_grid_level = grid_level - static_grid_level ## number of AMR moving grid levels
|
||||
|
||||
analysis_level = 0
|
||||
refinement_level = 3 ## time refinement start from this grid level
|
||||
|
||||
largest_box_xyz_max = [320.0, 320.0, 320.0] ## scale of the largest box
|
||||
## not ne cess ary to be cubic for "Patch" grid s tructure
|
||||
## need to be a cubic box for "Shell-Patch" grid structure
|
||||
largest_box_xyz_min = - numpy.array(largest_box_xyz_max)
|
||||
|
||||
static_grid_number = 48 ## grid points of each static AMR grid (in x direction) (Reduced from 96)
|
||||
## (grid points in y and z directions are automatically adjusted)
|
||||
moving_grid_number = 24 ## grid points of each moving AMR grid (Reduced from 48)
|
||||
shell_grid_number = [32, 32, 100] ## grid points of Shell-Patch grid
|
||||
## in (phi, theta, r) direction
|
||||
devide_factor = 2.0 ## resolution between different grid levels dh0/dh1, only support 2.0 now
|
||||
|
||||
|
||||
static_grid_type = 'Linear' ## AMR static grid structure , only supports "Linear"
|
||||
moving_grid_type = 'Linear' ## AMR moving grid structure , only supports "Linear"
|
||||
|
||||
quarter_sphere_number = 48 ## grid number of 1/4 s pher ical surface (Reduced from 96)
|
||||
## (which is needed for evaluating the spherical surface integral)
|
||||
|
||||
#################################################
|
||||
|
||||
|
||||
#################################################
|
||||
|
||||
## Setting the puncture information
|
||||
|
||||
puncture_number = 2
|
||||
|
||||
position_BH = numpy.zeros( (puncture_number, 3) )
|
||||
parameter_BH = numpy.zeros( (puncture_number, 3) )
|
||||
dimensionless_spin_BH = numpy.zeros( (puncture_number, 3) )
|
||||
momentum_BH = numpy.zeros( (puncture_number, 3) )
|
||||
|
||||
puncture_data_set = "Manually" ## Method to give Puncture’s positions and momentum
|
||||
## choose "Manually" or "Automatically-BBH"
|
||||
## Prefer to choose "Manually", because "Automatically-BBH" is developing now
|
||||
|
||||
## initial orbital distance and ellipticity for BBHs system
|
||||
## ( needed for "Automatically-BBH" case , not affect the "Manually" case )
|
||||
Distance = 10.0
|
||||
e0 = 0.0
|
||||
|
||||
## black hole parameter (M Q* a*)
|
||||
parameter_BH[0] = [ 36.0/(36.0+29.0), 0.0, +0.31 ]
|
||||
parameter_BH[1] = [ 29.0/(36.0+29.0), 0.0, -0.46 ]
|
||||
## dimensionless spin in each direction
|
||||
dimensionless_spin_BH[0] = [ 0.0, 0.0, +0.31 ]
|
||||
dimensionless_spin_BH[1] = [ 0.0, 0.0, -0.46 ]
|
||||
|
||||
## use Brugmann's convention
|
||||
## -----0-----> y
|
||||
## - +
|
||||
|
||||
#---------------------------------------------
|
||||
|
||||
## If puncture_data_set is chosen to be "Manually", it is necessary to set the position and momentum of each puncture manually
|
||||
|
||||
## initial position for each puncture
|
||||
position_BH[0] = [ 0.0, 10.0*29.0/(36.0+29.0), 0.0 ]
|
||||
position_BH[1] = [ 0.0, -10.0*36.0/(36.0+29.0), 0.0 ]
|
||||
|
||||
## initial mumentum for each puncture
|
||||
## (needed for "Manually" case, does not affect the "Automatically-BBH" case)
|
||||
momentum_BH[0] = [ -0.09530152296974252, -0.00084541526517121, 0.0 ]
|
||||
momentum_BH[1] = [ +0.09530152296974252, +0.00084541526517121, 0.0 ]
|
||||
|
||||
|
||||
#################################################
|
||||
|
||||
|
||||
#################################################
|
||||
|
||||
## Setting the gravitational wave information
|
||||
|
||||
GW_L_max = 4 ## maximal L number in gravitational wave
|
||||
GW_M_max = 4 ## maximal M number in gravitational wave
|
||||
Detector_Number = 12 ## number of dector
|
||||
Detector_Rmin = 50.0 ## nearest dector distance
|
||||
Detector_Rmax = 160.0 ## farest dector distance
|
||||
|
||||
#################################################
|
||||
|
||||
|
||||
#################################################
|
||||
|
||||
## Setting the apprent horizon
|
||||
|
||||
AHF_Find = "no" ## whether to find the apparent horizon: choose "yes" or "no"
|
||||
|
||||
AHF_Find_Every = 24
|
||||
AHF_Dump_Time = 20.0
|
||||
|
||||
#################################################
|
||||
|
||||
|
||||
#################################################
|
||||
|
||||
## Other parameters (testing)
|
||||
## Only influence the Equation_Class = "BSSN-EScalar" case
|
||||
|
||||
FR_a2 = 3.0 ## f(R) = R + a2 * R^2
|
||||
FR_l2 = 10000.0
|
||||
FR_phi0 = 0.00005
|
||||
FR_r0 = 120.0
|
||||
FR_sigma0 = 8.0
|
||||
FR_Choice = 2 ## Choice options: 1 2 3 4 5
|
||||
## 1: phi(r) = phi0 * Exp(-(r-r0)**2/sigma0)
|
||||
## V(r) = 0
|
||||
## 2: phi(r) = phi0 * a2^2/(1+a2^2)
|
||||
## V(r) = Exp(-8*Sqrt(PI/3)*phi(r)) * (1-Exp(4*Sqrt(PI/3)*phi(r)))**2 / (32*PI*a2)
|
||||
## 3: Schrodinger-Newton gived by system phi(r)
|
||||
## V(r) = Exp(-8*Sqrt(PI/3)*phi(r)) * (1-Exp(4*Sqrt(PI/3)*phi(r)))**2 / (32*PI*a2)
|
||||
## 4: phi(r) = phi0 * 0.5 * ( tanh((r+r0)/sigma0) - tanh((r-r0)/sigma0) )
|
||||
## V(r) = 0
|
||||
## f(R) = R + a2*R^2 with a2 = +oo
|
||||
## 5: phi(r) = phi0 * Exp(-(r-r0)**2/sigma)
|
||||
## V(r) = 0
|
||||
|
||||
#################################################
|
||||
|
||||
|
||||
#################################################
|
||||
|
||||
## Other parameters (testing)
|
||||
## (please do not change if not necessary)
|
||||
|
||||
boundary_choice = "BAM-choice" ## Sommerfeld boundary condition : choose "BAM-choice" or "Shibata-choice"
|
||||
## prefer "BAM-choice"
|
||||
|
||||
gauge_choice = 0 ## gauge choice
|
||||
## 0: B^i gauge
|
||||
## 1: David's puncture gauge
|
||||
## 2: MB B^i gauge
|
||||
## 3: RIT B^i gauge
|
||||
## 4: MB beta gauge
|
||||
## 5: RIT beta gauge
|
||||
## 6: MGB1 B^i gauge
|
||||
## 7: MGB2 B^i gauge
|
||||
## prefer 0 or 1
|
||||
|
||||
tetrad_type = 2 ## tetradtype
|
||||
## v:r; u: phi; w: theta
|
||||
## v^a = (x,y,z)
|
||||
## 0: orthonormal order: v,u,w
|
||||
## v^a = (x,y,z)
|
||||
## m = (phi - i theta)/sqrt(2)
|
||||
## following Frans, Eq.(8) of PRD 75, 124018(2007)
|
||||
## 1: orthonormal order: w,u,v
|
||||
## m = (theta + i phi)/sqrt(2)
|
||||
## following Sperhake, Eq.(3.2) of PRD 85, 124062(2012)
|
||||
## 2: orthonormal order: v,u,w
|
||||
## v_a = (x,y,z)
|
||||
## m = (phi - i theta)/sqrt(2)
|
||||
## following Frans, Eq.(8) of PRD 75, 124018(2007)
|
||||
## this version recommend set to 2
|
||||
## prefer 2
|
||||
|
||||
#################################################
|
||||
@@ -1,224 +0,0 @@
|
||||
##################################################################
|
||||
##
|
||||
## AMSS-NCKU Numerical Relativity Mini Test Program
|
||||
## Author: Assistant (based on Xiaoqu's code)
|
||||
## 2026/01/20
|
||||
##
|
||||
## This script runs a scaled-down version of the GW150914 test case
|
||||
## suitable for laptop testing.
|
||||
##
|
||||
##################################################################
|
||||
|
||||
import os
|
||||
import shutil
|
||||
import sys
|
||||
import time
|
||||
|
||||
# --- Context Manager for Input File Swapping ---
|
||||
class InputFileSwapper:
|
||||
def __init__(self, mini_file="AMSS_NCKU_Input_Mini.py", target_file="AMSS_NCKU_Input.py"):
|
||||
self.mini_file = mini_file
|
||||
self.target_file = target_file
|
||||
self.backup_file = target_file + ".bak"
|
||||
self.swapped = False
|
||||
|
||||
def __enter__(self):
|
||||
print(f"[MiniProgram] Swapping {self.target_file} with {self.mini_file}...")
|
||||
if os.path.exists(self.target_file):
|
||||
shutil.move(self.target_file, self.backup_file)
|
||||
shutil.copy(self.mini_file, self.target_file)
|
||||
self.swapped = True
|
||||
return self
|
||||
|
||||
def __exit__(self, exc_type, exc_value, traceback):
|
||||
if self.swapped:
|
||||
print(f"[MiniProgram] Restoring original {self.target_file}...")
|
||||
os.remove(self.target_file)
|
||||
if os.path.exists(self.backup_file):
|
||||
shutil.move(self.backup_file, self.target_file)
|
||||
|
||||
def main():
|
||||
# Use the swapper to ensure all imported modules see the mini configuration
|
||||
with InputFileSwapper():
|
||||
|
||||
# Import modules AFTER swapping input file
|
||||
try:
|
||||
import AMSS_NCKU_Input as input_data
|
||||
import print_information
|
||||
import setup
|
||||
import numerical_grid
|
||||
import generate_macrodef
|
||||
import makefile_and_run
|
||||
import generate_TwoPuncture_input
|
||||
import renew_puncture_parameter
|
||||
import plot_xiaoqu
|
||||
import plot_GW_strain_amplitude_xiaoqu
|
||||
except ImportError as e:
|
||||
print(f"Error importing modules: {e}")
|
||||
return
|
||||
|
||||
print_information.print_program_introduction()
|
||||
|
||||
print("\n" + "#"*60)
|
||||
print(" RUNNING MINI TEST CASE: GW150914-mini")
|
||||
print("#"*60 + "\n")
|
||||
|
||||
# --- Directory Setup ---
|
||||
File_directory = os.path.join(input_data.File_directory)
|
||||
|
||||
if os.path.exists(File_directory):
|
||||
print(f" Output directory '{File_directory}' exists. Removing for mini test...")
|
||||
shutil.rmtree(File_directory, ignore_errors=True)
|
||||
|
||||
os.mkdir(File_directory)
|
||||
shutil.copy("AMSS_NCKU_Input.py", File_directory) # Copies the current (mini) input
|
||||
|
||||
output_directory = os.path.join(File_directory, "AMSS_NCKU_output")
|
||||
os.mkdir(output_directory)
|
||||
|
||||
binary_results_directory = os.path.join(output_directory, input_data.Output_directory)
|
||||
os.mkdir(binary_results_directory)
|
||||
|
||||
figure_directory = os.path.join(File_directory, "figure")
|
||||
os.mkdir(figure_directory)
|
||||
|
||||
print(" Output directories generated.\n")
|
||||
|
||||
# --- Setup and Input Generation ---
|
||||
setup.print_input_data(File_directory)
|
||||
setup.generate_AMSSNCKU_input()
|
||||
setup.print_puncture_information()
|
||||
|
||||
print("\n Generating AMSS-NCKU input parfile...")
|
||||
numerical_grid.append_AMSSNCKU_cgh_input()
|
||||
|
||||
print("\n Plotting initial grid...")
|
||||
numerical_grid.plot_initial_grid()
|
||||
|
||||
print("\n Generating macro files...")
|
||||
generate_macrodef.generate_macrodef_h()
|
||||
generate_macrodef.generate_macrodef_fh()
|
||||
|
||||
# --- Compilation Preparation ---
|
||||
print("\n Preparing to compile and run...")
|
||||
|
||||
AMSS_NCKU_source_path = "AMSS_NCKU_source"
|
||||
AMSS_NCKU_source_copy = os.path.join(File_directory, "AMSS_NCKU_source_copy")
|
||||
|
||||
if not os.path.exists(AMSS_NCKU_source_path):
|
||||
print(" Error: AMSS_NCKU_source not found! Please run in the project root.")
|
||||
return
|
||||
|
||||
shutil.copytree(AMSS_NCKU_source_path, AMSS_NCKU_source_copy)
|
||||
|
||||
macrodef_h_path = os.path.join(File_directory, "macrodef.h")
|
||||
macrodef_fh_path = os.path.join(File_directory, "macrodef.fh")
|
||||
|
||||
shutil.copy2(macrodef_h_path, AMSS_NCKU_source_copy)
|
||||
shutil.copy2(macrodef_fh_path, AMSS_NCKU_source_copy)
|
||||
|
||||
# --- Compilation ---
|
||||
cwd = os.getcwd()
|
||||
os.chdir(AMSS_NCKU_source_copy)
|
||||
|
||||
print(" Compiling ABE...")
|
||||
makefile_and_run.makefile_ABE()
|
||||
|
||||
if (input_data.Initial_Data_Method == "Ansorg-TwoPuncture" ):
|
||||
print(" Compiling TwoPunctureABE...")
|
||||
makefile_and_run.makefile_TwoPunctureABE()
|
||||
|
||||
os.chdir(cwd)
|
||||
|
||||
# --- Copy Executables ---
|
||||
if (input_data.GPU_Calculation == "no"):
|
||||
ABE_file = os.path.join(AMSS_NCKU_source_copy, "ABE")
|
||||
else:
|
||||
ABE_file = os.path.join(AMSS_NCKU_source_copy, "ABEGPU")
|
||||
|
||||
if not os.path.exists(ABE_file):
|
||||
print(" Error: ABE executable compilation failed.")
|
||||
return
|
||||
|
||||
shutil.copy2(ABE_file, output_directory)
|
||||
|
||||
TwoPuncture_file = os.path.join(AMSS_NCKU_source_copy, "TwoPunctureABE")
|
||||
if (input_data.Initial_Data_Method == "Ansorg-TwoPuncture" ):
|
||||
if not os.path.exists(TwoPuncture_file):
|
||||
print(" Error: TwoPunctureABE compilation failed.")
|
||||
return
|
||||
shutil.copy2(TwoPuncture_file, output_directory)
|
||||
|
||||
# --- Execution ---
|
||||
start_time = time.time()
|
||||
|
||||
if (input_data.Initial_Data_Method == "Ansorg-TwoPuncture" ):
|
||||
print("\n Generating TwoPuncture input...")
|
||||
generate_TwoPuncture_input.generate_AMSSNCKU_TwoPuncture_input()
|
||||
|
||||
AMSS_NCKU_TwoPuncture_inputfile = 'AMSS-NCKU-TwoPuncture.input'
|
||||
AMSS_NCKU_TwoPuncture_inputfile_path = os.path.join( File_directory, AMSS_NCKU_TwoPuncture_inputfile )
|
||||
shutil.copy2( AMSS_NCKU_TwoPuncture_inputfile_path, os.path.join(output_directory, 'TwoPunctureinput.par') )
|
||||
|
||||
print(" Running TwoPunctureABE...")
|
||||
os.chdir(output_directory)
|
||||
makefile_and_run.run_TwoPunctureABE()
|
||||
os.chdir(cwd)
|
||||
|
||||
# Update Puncture Parameter
|
||||
renew_puncture_parameter.append_AMSSNCKU_BSSN_input(File_directory, output_directory)
|
||||
|
||||
AMSS_NCKU_inputfile = 'AMSS-NCKU.input'
|
||||
AMSS_NCKU_inputfile_path = os.path.join(File_directory, AMSS_NCKU_inputfile)
|
||||
shutil.copy2( AMSS_NCKU_inputfile_path, os.path.join(output_directory, 'input.par') )
|
||||
|
||||
print("\n Input files ready. Launching ABE...")
|
||||
|
||||
os.chdir(output_directory)
|
||||
makefile_and_run.run_ABE()
|
||||
os.chdir(cwd)
|
||||
|
||||
end_time = time.time()
|
||||
elapsed_time = end_time - start_time
|
||||
|
||||
# --- Post-processing ---
|
||||
print("\n Copying output files for inspection...")
|
||||
AMSS_NCKU_error_file_path = os.path.join(binary_results_directory, "setting.par")
|
||||
if os.path.exists(AMSS_NCKU_error_file_path):
|
||||
shutil.copy( AMSS_NCKU_error_file_path, os.path.join(output_directory, "AMSSNCKU_setting_parameter") )
|
||||
|
||||
AMSS_NCKU_error_file_path = os.path.join(binary_results_directory, "Error.log")
|
||||
if os.path.exists(AMSS_NCKU_error_file_path):
|
||||
shutil.copy( AMSS_NCKU_error_file_path, os.path.join(output_directory, "Error.log") )
|
||||
|
||||
for fname in ["bssn_BH.dat", "bssn_ADMQs.dat", "bssn_psi4.dat", "bssn_constraint.dat"]:
|
||||
fpath = os.path.join(binary_results_directory, fname)
|
||||
if os.path.exists(fpath):
|
||||
shutil.copy(fpath, os.path.join(output_directory, fname))
|
||||
|
||||
# --- Plotting ---
|
||||
print("\n Plotting results...")
|
||||
try:
|
||||
plot_xiaoqu.generate_puncture_orbit_plot( binary_results_directory, figure_directory )
|
||||
plot_xiaoqu.generate_puncture_orbit_plot3D( binary_results_directory, figure_directory )
|
||||
plot_xiaoqu.generate_puncture_distence_plot( binary_results_directory, figure_directory )
|
||||
|
||||
for i in range(input_data.Detector_Number):
|
||||
plot_xiaoqu.generate_gravitational_wave_psi4_plot( binary_results_directory, figure_directory, i )
|
||||
plot_GW_strain_amplitude_xiaoqu.generate_gravitational_wave_amplitude_plot( binary_results_directory, figure_directory, i )
|
||||
|
||||
for i in range(input_data.Detector_Number):
|
||||
plot_xiaoqu.generate_ADMmass_plot( binary_results_directory, figure_directory, i )
|
||||
|
||||
for i in range(input_data.grid_level):
|
||||
plot_xiaoqu.generate_constraint_check_plot( binary_results_directory, figure_directory, i )
|
||||
|
||||
plot_xiaoqu.generate_binary_data_plot( binary_results_directory, figure_directory )
|
||||
except Exception as e:
|
||||
print(f"Warning: Plotting failed: {e}")
|
||||
|
||||
print(f"\n Program Cost = {elapsed_time:.2f} Seconds \n")
|
||||
print(" AMSS-NCKU-Python simulation finished (Mini Test).\n")
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -9,9 +9,19 @@
|
||||
##################################################################
|
||||
|
||||
|
||||
##################################################################
|
||||
|
||||
## Print program introduction
|
||||
##################################################################
|
||||
|
||||
## 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
|
||||
|
||||
import print_information
|
||||
|
||||
@@ -422,31 +432,36 @@ print( " Plotting the txt and binary results data from the AMSS-NCKU simulation
|
||||
print( )
|
||||
|
||||
|
||||
import plot_xiaoqu
|
||||
import plot_GW_strain_amplitude_xiaoqu
|
||||
|
||||
## Plot black hole trajectory
|
||||
plot_xiaoqu.generate_puncture_orbit_plot( binary_results_directory, figure_directory )
|
||||
plot_xiaoqu.generate_puncture_orbit_plot3D( binary_results_directory, figure_directory )
|
||||
|
||||
## Plot black hole separation vs. time
|
||||
plot_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_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 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 stored binary data
|
||||
plot_xiaoqu.generate_binary_data_plot( binary_results_directory, figure_directory )
|
||||
import plot_xiaoqu
|
||||
import plot_GW_strain_amplitude_xiaoqu
|
||||
from parallel_plot_helper import run_plot_tasks_parallel
|
||||
|
||||
plot_tasks = []
|
||||
|
||||
## Plot black hole trajectory
|
||||
plot_tasks.append( ( plot_xiaoqu.generate_puncture_orbit_plot, (binary_results_directory, figure_directory) ) )
|
||||
plot_tasks.append( ( plot_xiaoqu.generate_puncture_orbit_plot3D, (binary_results_directory, figure_directory) ) )
|
||||
|
||||
## Plot black hole separation vs. time
|
||||
plot_tasks.append( ( plot_xiaoqu.generate_puncture_distence_plot, (binary_results_directory, figure_directory) ) )
|
||||
|
||||
## Plot gravitational waveforms (psi4 and strain amplitude)
|
||||
for i in range(input_data.Detector_Number):
|
||||
plot_tasks.append( ( plot_xiaoqu.generate_gravitational_wave_psi4_plot, (binary_results_directory, figure_directory, i) ) )
|
||||
plot_tasks.append( ( plot_GW_strain_amplitude_xiaoqu.generate_gravitational_wave_amplitude_plot, (binary_results_directory, figure_directory, i) ) )
|
||||
|
||||
## Plot ADM mass evolution
|
||||
for i in range(input_data.Detector_Number):
|
||||
plot_tasks.append( ( plot_xiaoqu.generate_ADMmass_plot, (binary_results_directory, figure_directory, i) ) )
|
||||
|
||||
## Plot Hamiltonian constraint violation over time
|
||||
for i in range(input_data.grid_level):
|
||||
plot_tasks.append( ( plot_xiaoqu.generate_constraint_check_plot, (binary_results_directory, figure_directory, i) ) )
|
||||
|
||||
run_plot_tasks_parallel(plot_tasks)
|
||||
|
||||
## Plot stored binary data
|
||||
plot_xiaoqu.generate_binary_data_plot( binary_results_directory, figure_directory )
|
||||
|
||||
print( )
|
||||
print( f" This Program Cost = {elapsed_time} Seconds " )
|
||||
|
||||
@@ -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()
|
||||
@@ -37,51 +37,57 @@ close(77)
|
||||
end program checkFFT
|
||||
#endif
|
||||
|
||||
!-------------
|
||||
! Optimized FFT using Intel oneMKL DFTI
|
||||
! Mathematical equivalence: Standard DFT definition
|
||||
! Forward (isign=1): X[k] = sum_{n=0}^{N-1} x[n] * exp(-2*pi*i*k*n/N)
|
||||
! Backward (isign=-1): X[k] = sum_{n=0}^{N-1} x[n] * exp(+2*pi*i*k*n/N)
|
||||
! Input/Output: dataa is interleaved complex array [Re(0),Im(0),Re(1),Im(1),...]
|
||||
!-------------
|
||||
SUBROUTINE four1(dataa,nn,isign)
|
||||
use MKL_DFTI
|
||||
implicit none
|
||||
INTEGER, intent(in) :: isign, nn
|
||||
DOUBLE PRECISION, dimension(2*nn), intent(inout) :: dataa
|
||||
|
||||
type(DFTI_DESCRIPTOR), pointer :: desc
|
||||
integer :: status
|
||||
|
||||
! Create DFTI descriptor for 1D complex-to-complex transform
|
||||
status = DftiCreateDescriptor(desc, DFTI_DOUBLE, DFTI_COMPLEX, 1, nn)
|
||||
if (status /= 0) return
|
||||
|
||||
! Set input/output storage as interleaved complex (default)
|
||||
status = DftiSetValue(desc, DFTI_PLACEMENT, DFTI_INPLACE)
|
||||
if (status /= 0) then
|
||||
status = DftiFreeDescriptor(desc)
|
||||
return
|
||||
INTEGER::isign,nn
|
||||
double precision,dimension(2*nn)::dataa
|
||||
INTEGER::i,istep,j,m,mmax,n
|
||||
double precision::tempi,tempr
|
||||
DOUBLE PRECISION::theta,wi,wpi,wpr,wr,wtemp
|
||||
n=2*nn
|
||||
j=1
|
||||
do i=1,n,2
|
||||
if(j.gt.i)then
|
||||
tempr=dataa(j)
|
||||
tempi=dataa(j+1)
|
||||
dataa(j)=dataa(i)
|
||||
dataa(j+1)=dataa(i+1)
|
||||
dataa(i)=tempr
|
||||
dataa(i+1)=tempi
|
||||
endif
|
||||
m=nn
|
||||
1 if ((m.ge.2).and.(j.gt.m)) then
|
||||
j=j-m
|
||||
m=m/2
|
||||
goto 1
|
||||
endif
|
||||
j=j+m
|
||||
enddo
|
||||
mmax=2
|
||||
2 if (n.gt.mmax) then
|
||||
istep=2*mmax
|
||||
theta=6.28318530717959d0/(isign*mmax)
|
||||
wpr=-2.d0*sin(0.5d0*theta)**2
|
||||
wpi=sin(theta)
|
||||
wr=1.d0
|
||||
wi=0.d0
|
||||
do m=1,mmax,2
|
||||
do i=m,n,istep
|
||||
j=i+mmax
|
||||
tempr=sngl(wr)*dataa(j)-sngl(wi)*dataa(j+1)
|
||||
tempi=sngl(wr)*dataa(j+1)+sngl(wi)*dataa(j)
|
||||
dataa(j)=dataa(i)-tempr
|
||||
dataa(j+1)=dataa(i+1)-tempi
|
||||
dataa(i)=dataa(i)+tempr
|
||||
dataa(i+1)=dataa(i+1)+tempi
|
||||
enddo
|
||||
wtemp=wr
|
||||
wr=wr*wpr-wi*wpi+wr
|
||||
wi=wi*wpr+wtemp*wpi+wi
|
||||
enddo
|
||||
mmax=istep
|
||||
goto 2
|
||||
endif
|
||||
|
||||
! Commit the descriptor
|
||||
status = DftiCommitDescriptor(desc)
|
||||
if (status /= 0) then
|
||||
status = DftiFreeDescriptor(desc)
|
||||
return
|
||||
endif
|
||||
|
||||
! Execute FFT based on direction
|
||||
if (isign == 1) then
|
||||
! Forward FFT: exp(-2*pi*i*k*n/N)
|
||||
status = DftiComputeForward(desc, dataa)
|
||||
else
|
||||
! Backward FFT: exp(+2*pi*i*k*n/N)
|
||||
status = DftiComputeBackward(desc, dataa)
|
||||
endif
|
||||
|
||||
! Free descriptor
|
||||
status = DftiFreeDescriptor(desc)
|
||||
|
||||
return
|
||||
END SUBROUTINE four1
|
||||
|
||||
@@ -313,7 +313,7 @@ MyList<Block> *Parallel::distribute(MyList<Patch> *PatchLIST, int cpusize, int i
|
||||
|
||||
int split_size, min_size, block_size = 0;
|
||||
|
||||
int min_width = Mymax(2 * ghost_width + 2, buffer_width + 2);
|
||||
int min_width = 2 * Mymax(ghost_width, buffer_width);
|
||||
int nxyz[dim], mmin_width[dim], min_shape[dim];
|
||||
|
||||
MyList<Patch> *PLi = PatchLIST;
|
||||
@@ -641,7 +641,7 @@ MyList<Block> *Parallel::distribute(MyList<Patch> *PatchLIST, int cpusize, int i
|
||||
|
||||
int split_size, min_size, block_size = 0;
|
||||
|
||||
int min_width = Mymax(2 * ghost_width + 2, buffer_width + 2);
|
||||
int min_width = 2 * Mymax(ghost_width, buffer_width);
|
||||
int nxyz[dim], mmin_width[dim], min_shape[dim];
|
||||
|
||||
MyList<Patch> *PLi = PatchLIST;
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -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
|
||||
@@ -32,7 +33,7 @@ private:
|
||||
int npoints_A, npoints_B, npoints_phi;
|
||||
|
||||
double target_M_plus, target_M_minus;
|
||||
|
||||
|
||||
double admMass;
|
||||
|
||||
double adm_tol;
|
||||
@@ -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)
|
||||
@@ -141,4 +164,4 @@ public:
|
||||
void SpecCoef(parameters par, int ivar, double *v, double *cf);
|
||||
};
|
||||
|
||||
#endif /* TWO_PUNCTURES_H */
|
||||
#endif /* TWO_PUNCTURES_H */
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1939,309 +1939,6 @@
|
||||
return
|
||||
|
||||
end subroutine fddyz
|
||||
subroutine fderivs_batch4(ex,f1,f2,f3,f4, &
|
||||
f1x,f1y,f1z,f2x,f2y,f2z,f3x,f3y,f3z,f4x,f4y,f4z, &
|
||||
X,Y,Z,SYM1,SYM2,SYM3,symmetry,onoff)
|
||||
implicit none
|
||||
|
||||
integer, intent(in ):: ex(1:3),symmetry,onoff
|
||||
real*8, dimension(ex(1),ex(2),ex(3)), intent(in ):: f1,f2,f3,f4
|
||||
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f1x,f1y,f1z
|
||||
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f2x,f2y,f2z
|
||||
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f3x,f3y,f3z
|
||||
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f4x,f4y,f4z
|
||||
real*8, intent(in) :: X(ex(1)),Y(ex(2)),Z(ex(3))
|
||||
real*8, intent(in ):: SYM1,SYM2,SYM3
|
||||
|
||||
!~~~~~~ other variables
|
||||
|
||||
real*8 :: dX,dY,dZ
|
||||
real*8,dimension(-1:ex(1),-1:ex(2),-1:ex(3)) :: fh1,fh2,fh3,fh4
|
||||
real*8, dimension(3) :: SoA
|
||||
integer :: imin,jmin,kmin,imax,jmax,kmax,i,j,k
|
||||
real*8 :: d12dx,d12dy,d12dz,d2dx,d2dy,d2dz
|
||||
integer, parameter :: NO_SYMM = 0, EQ_SYMM = 1, OCTANT = 2
|
||||
real*8, parameter :: ZEO=0.d0,ONE=1.d0
|
||||
real*8, parameter :: TWO=2.d0,EIT=8.d0
|
||||
real*8, parameter :: F12=1.2d1
|
||||
|
||||
dX = X(2)-X(1)
|
||||
dY = Y(2)-Y(1)
|
||||
dZ = Z(2)-Z(1)
|
||||
|
||||
imax = ex(1)
|
||||
jmax = ex(2)
|
||||
kmax = ex(3)
|
||||
|
||||
imin = 1
|
||||
jmin = 1
|
||||
kmin = 1
|
||||
if(Symmetry > NO_SYMM .and. dabs(Z(1)) < dZ) kmin = -1
|
||||
if(Symmetry > EQ_SYMM .and. dabs(X(1)) < dX) imin = -1
|
||||
if(Symmetry > EQ_SYMM .and. dabs(Y(1)) < dY) jmin = -1
|
||||
|
||||
SoA(1) = SYM1
|
||||
SoA(2) = SYM2
|
||||
SoA(3) = SYM3
|
||||
|
||||
call symmetry_bd(2,ex,f1,fh1,SoA)
|
||||
call symmetry_bd(2,ex,f2,fh2,SoA)
|
||||
call symmetry_bd(2,ex,f3,fh3,SoA)
|
||||
call symmetry_bd(2,ex,f4,fh4,SoA)
|
||||
|
||||
d12dx = ONE/F12/dX
|
||||
d12dy = ONE/F12/dY
|
||||
d12dz = ONE/F12/dZ
|
||||
|
||||
d2dx = ONE/TWO/dX
|
||||
d2dy = ONE/TWO/dY
|
||||
d2dz = ONE/TWO/dZ
|
||||
|
||||
f1x = ZEO; f1y = ZEO; f1z = ZEO
|
||||
f2x = ZEO; f2y = ZEO; f2z = ZEO
|
||||
f3x = ZEO; f3y = ZEO; f3z = ZEO
|
||||
f4x = ZEO; f4y = ZEO; f4z = ZEO
|
||||
|
||||
do k=1,ex(3)-1
|
||||
do j=1,ex(2)-1
|
||||
do i=1,ex(1)-1
|
||||
if(i+2 <= imax .and. i-2 >= imin .and. &
|
||||
j+2 <= jmax .and. j-2 >= jmin .and. &
|
||||
k+2 <= kmax .and. k-2 >= kmin) then
|
||||
f1x(i,j,k)=d12dx*(fh1(i-2,j,k)-EIT*fh1(i-1,j,k)+EIT*fh1(i+1,j,k)-fh1(i+2,j,k))
|
||||
f1y(i,j,k)=d12dy*(fh1(i,j-2,k)-EIT*fh1(i,j-1,k)+EIT*fh1(i,j+1,k)-fh1(i,j+2,k))
|
||||
f1z(i,j,k)=d12dz*(fh1(i,j,k-2)-EIT*fh1(i,j,k-1)+EIT*fh1(i,j,k+1)-fh1(i,j,k+2))
|
||||
|
||||
f2x(i,j,k)=d12dx*(fh2(i-2,j,k)-EIT*fh2(i-1,j,k)+EIT*fh2(i+1,j,k)-fh2(i+2,j,k))
|
||||
f2y(i,j,k)=d12dy*(fh2(i,j-2,k)-EIT*fh2(i,j-1,k)+EIT*fh2(i,j+1,k)-fh2(i,j+2,k))
|
||||
f2z(i,j,k)=d12dz*(fh2(i,j,k-2)-EIT*fh2(i,j,k-1)+EIT*fh2(i,j,k+1)-fh2(i,j,k+2))
|
||||
|
||||
f3x(i,j,k)=d12dx*(fh3(i-2,j,k)-EIT*fh3(i-1,j,k)+EIT*fh3(i+1,j,k)-fh3(i+2,j,k))
|
||||
f3y(i,j,k)=d12dy*(fh3(i,j-2,k)-EIT*fh3(i,j-1,k)+EIT*fh3(i,j+1,k)-fh3(i,j+2,k))
|
||||
f3z(i,j,k)=d12dz*(fh3(i,j,k-2)-EIT*fh3(i,j,k-1)+EIT*fh3(i,j,k+1)-fh3(i,j,k+2))
|
||||
|
||||
f4x(i,j,k)=d12dx*(fh4(i-2,j,k)-EIT*fh4(i-1,j,k)+EIT*fh4(i+1,j,k)-fh4(i+2,j,k))
|
||||
f4y(i,j,k)=d12dy*(fh4(i,j-2,k)-EIT*fh4(i,j-1,k)+EIT*fh4(i,j+1,k)-fh4(i,j+2,k))
|
||||
f4z(i,j,k)=d12dz*(fh4(i,j,k-2)-EIT*fh4(i,j,k-1)+EIT*fh4(i,j,k+1)-fh4(i,j,k+2))
|
||||
elseif(i+1 <= imax .and. i-1 >= imin .and. &
|
||||
j+1 <= jmax .and. j-1 >= jmin .and. &
|
||||
k+1 <= kmax .and. k-1 >= kmin) then
|
||||
f1x(i,j,k)=d2dx*(-fh1(i-1,j,k)+fh1(i+1,j,k))
|
||||
f1y(i,j,k)=d2dy*(-fh1(i,j-1,k)+fh1(i,j+1,k))
|
||||
f1z(i,j,k)=d2dz*(-fh1(i,j,k-1)+fh1(i,j,k+1))
|
||||
|
||||
f2x(i,j,k)=d2dx*(-fh2(i-1,j,k)+fh2(i+1,j,k))
|
||||
f2y(i,j,k)=d2dy*(-fh2(i,j-1,k)+fh2(i,j+1,k))
|
||||
f2z(i,j,k)=d2dz*(-fh2(i,j,k-1)+fh2(i,j,k+1))
|
||||
|
||||
f3x(i,j,k)=d2dx*(-fh3(i-1,j,k)+fh3(i+1,j,k))
|
||||
f3y(i,j,k)=d2dy*(-fh3(i,j-1,k)+fh3(i,j+1,k))
|
||||
f3z(i,j,k)=d2dz*(-fh3(i,j,k-1)+fh3(i,j,k+1))
|
||||
|
||||
f4x(i,j,k)=d2dx*(-fh4(i-1,j,k)+fh4(i+1,j,k))
|
||||
f4y(i,j,k)=d2dy*(-fh4(i,j-1,k)+fh4(i,j+1,k))
|
||||
f4z(i,j,k)=d2dz*(-fh4(i,j,k-1)+fh4(i,j,k+1))
|
||||
endif
|
||||
enddo
|
||||
enddo
|
||||
enddo
|
||||
|
||||
return
|
||||
|
||||
end subroutine fderivs_batch4
|
||||
!-----------------------------------------------------------------------------
|
||||
! batch first derivatives (3 fields), same symmetry setup
|
||||
!-----------------------------------------------------------------------------
|
||||
subroutine fderivs_batch3(ex,f1,f2,f3, &
|
||||
f1x,f1y,f1z,f2x,f2y,f2z,f3x,f3y,f3z, &
|
||||
X,Y,Z,SYM1,SYM2,SYM3,symmetry,onoff)
|
||||
implicit none
|
||||
|
||||
integer, intent(in ):: ex(1:3),symmetry,onoff
|
||||
real*8, dimension(ex(1),ex(2),ex(3)), intent(in ):: f1,f2,f3
|
||||
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f1x,f1y,f1z
|
||||
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f2x,f2y,f2z
|
||||
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f3x,f3y,f3z
|
||||
real*8, intent(in) :: X(ex(1)),Y(ex(2)),Z(ex(3))
|
||||
real*8, intent(in ):: SYM1,SYM2,SYM3
|
||||
|
||||
!~~~~~~ other variables
|
||||
|
||||
real*8 :: dX,dY,dZ
|
||||
real*8,dimension(-1:ex(1),-1:ex(2),-1:ex(3)) :: fh1,fh2,fh3
|
||||
real*8, dimension(3) :: SoA
|
||||
integer :: imin,jmin,kmin,imax,jmax,kmax,i,j,k
|
||||
real*8 :: d12dx,d12dy,d12dz,d2dx,d2dy,d2dz
|
||||
integer, parameter :: NO_SYMM = 0, EQ_SYMM = 1, OCTANT = 2
|
||||
real*8, parameter :: ZEO=0.d0,ONE=1.d0
|
||||
real*8, parameter :: TWO=2.d0,EIT=8.d0
|
||||
real*8, parameter :: F12=1.2d1
|
||||
|
||||
dX = X(2)-X(1)
|
||||
dY = Y(2)-Y(1)
|
||||
dZ = Z(2)-Z(1)
|
||||
|
||||
imax = ex(1)
|
||||
jmax = ex(2)
|
||||
kmax = ex(3)
|
||||
|
||||
imin = 1
|
||||
jmin = 1
|
||||
kmin = 1
|
||||
if(Symmetry > NO_SYMM .and. dabs(Z(1)) < dZ) kmin = -1
|
||||
if(Symmetry > EQ_SYMM .and. dabs(X(1)) < dX) imin = -1
|
||||
if(Symmetry > EQ_SYMM .and. dabs(Y(1)) < dY) jmin = -1
|
||||
|
||||
SoA(1) = SYM1
|
||||
SoA(2) = SYM2
|
||||
SoA(3) = SYM3
|
||||
|
||||
call symmetry_bd(2,ex,f1,fh1,SoA)
|
||||
call symmetry_bd(2,ex,f2,fh2,SoA)
|
||||
call symmetry_bd(2,ex,f3,fh3,SoA)
|
||||
|
||||
d12dx = ONE/F12/dX
|
||||
d12dy = ONE/F12/dY
|
||||
d12dz = ONE/F12/dZ
|
||||
|
||||
d2dx = ONE/TWO/dX
|
||||
d2dy = ONE/TWO/dY
|
||||
d2dz = ONE/TWO/dZ
|
||||
|
||||
f1x = ZEO; f1y = ZEO; f1z = ZEO
|
||||
f2x = ZEO; f2y = ZEO; f2z = ZEO
|
||||
f3x = ZEO; f3y = ZEO; f3z = ZEO
|
||||
|
||||
do k=1,ex(3)-1
|
||||
do j=1,ex(2)-1
|
||||
do i=1,ex(1)-1
|
||||
if(i+2 <= imax .and. i-2 >= imin .and. &
|
||||
j+2 <= jmax .and. j-2 >= jmin .and. &
|
||||
k+2 <= kmax .and. k-2 >= kmin) then
|
||||
f1x(i,j,k)=d12dx*(fh1(i-2,j,k)-EIT*fh1(i-1,j,k)+EIT*fh1(i+1,j,k)-fh1(i+2,j,k))
|
||||
f1y(i,j,k)=d12dy*(fh1(i,j-2,k)-EIT*fh1(i,j-1,k)+EIT*fh1(i,j+1,k)-fh1(i,j+2,k))
|
||||
f1z(i,j,k)=d12dz*(fh1(i,j,k-2)-EIT*fh1(i,j,k-1)+EIT*fh1(i,j,k+1)-fh1(i,j,k+2))
|
||||
|
||||
f2x(i,j,k)=d12dx*(fh2(i-2,j,k)-EIT*fh2(i-1,j,k)+EIT*fh2(i+1,j,k)-fh2(i+2,j,k))
|
||||
f2y(i,j,k)=d12dy*(fh2(i,j-2,k)-EIT*fh2(i,j-1,k)+EIT*fh2(i,j+1,k)-fh2(i,j+2,k))
|
||||
f2z(i,j,k)=d12dz*(fh2(i,j,k-2)-EIT*fh2(i,j,k-1)+EIT*fh2(i,j,k+1)-fh2(i,j,k+2))
|
||||
|
||||
f3x(i,j,k)=d12dx*(fh3(i-2,j,k)-EIT*fh3(i-1,j,k)+EIT*fh3(i+1,j,k)-fh3(i+2,j,k))
|
||||
f3y(i,j,k)=d12dy*(fh3(i,j-2,k)-EIT*fh3(i,j-1,k)+EIT*fh3(i,j+1,k)-fh3(i,j+2,k))
|
||||
f3z(i,j,k)=d12dz*(fh3(i,j,k-2)-EIT*fh3(i,j,k-1)+EIT*fh3(i,j,k+1)-fh3(i,j,k+2))
|
||||
elseif(i+1 <= imax .and. i-1 >= imin .and. &
|
||||
j+1 <= jmax .and. j-1 >= jmin .and. &
|
||||
k+1 <= kmax .and. k-1 >= kmin) then
|
||||
f1x(i,j,k)=d2dx*(-fh1(i-1,j,k)+fh1(i+1,j,k))
|
||||
f1y(i,j,k)=d2dy*(-fh1(i,j-1,k)+fh1(i,j+1,k))
|
||||
f1z(i,j,k)=d2dz*(-fh1(i,j,k-1)+fh1(i,j,k+1))
|
||||
|
||||
f2x(i,j,k)=d2dx*(-fh2(i-1,j,k)+fh2(i+1,j,k))
|
||||
f2y(i,j,k)=d2dy*(-fh2(i,j-1,k)+fh2(i,j+1,k))
|
||||
f2z(i,j,k)=d2dz*(-fh2(i,j,k-1)+fh2(i,j,k+1))
|
||||
|
||||
f3x(i,j,k)=d2dx*(-fh3(i-1,j,k)+fh3(i+1,j,k))
|
||||
f3y(i,j,k)=d2dy*(-fh3(i,j-1,k)+fh3(i,j+1,k))
|
||||
f3z(i,j,k)=d2dz*(-fh3(i,j,k-1)+fh3(i,j,k+1))
|
||||
endif
|
||||
enddo
|
||||
enddo
|
||||
enddo
|
||||
|
||||
return
|
||||
|
||||
end subroutine fderivs_batch3
|
||||
!-----------------------------------------------------------------------------
|
||||
! batch first derivatives (2 fields), same symmetry setup
|
||||
!-----------------------------------------------------------------------------
|
||||
subroutine fderivs_batch2(ex,f1,f2, &
|
||||
f1x,f1y,f1z,f2x,f2y,f2z, &
|
||||
X,Y,Z,SYM1,SYM2,SYM3,symmetry,onoff)
|
||||
implicit none
|
||||
|
||||
integer, intent(in ):: ex(1:3),symmetry,onoff
|
||||
real*8, dimension(ex(1),ex(2),ex(3)), intent(in ):: f1,f2
|
||||
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f1x,f1y,f1z
|
||||
real*8, dimension(ex(1),ex(2),ex(3)), intent(out):: f2x,f2y,f2z
|
||||
real*8, intent(in) :: X(ex(1)),Y(ex(2)),Z(ex(3))
|
||||
real*8, intent(in ):: SYM1,SYM2,SYM3
|
||||
|
||||
!~~~~~~ other variables
|
||||
|
||||
real*8 :: dX,dY,dZ
|
||||
real*8,dimension(-1:ex(1),-1:ex(2),-1:ex(3)) :: fh1,fh2
|
||||
real*8, dimension(3) :: SoA
|
||||
integer :: imin,jmin,kmin,imax,jmax,kmax,i,j,k
|
||||
real*8 :: d12dx,d12dy,d12dz,d2dx,d2dy,d2dz
|
||||
integer, parameter :: NO_SYMM = 0, EQ_SYMM = 1, OCTANT = 2
|
||||
real*8, parameter :: ZEO=0.d0,ONE=1.d0
|
||||
real*8, parameter :: TWO=2.d0,EIT=8.d0
|
||||
real*8, parameter :: F12=1.2d1
|
||||
|
||||
dX = X(2)-X(1)
|
||||
dY = Y(2)-Y(1)
|
||||
dZ = Z(2)-Z(1)
|
||||
|
||||
imax = ex(1)
|
||||
jmax = ex(2)
|
||||
kmax = ex(3)
|
||||
|
||||
imin = 1
|
||||
jmin = 1
|
||||
kmin = 1
|
||||
if(Symmetry > NO_SYMM .and. dabs(Z(1)) < dZ) kmin = -1
|
||||
if(Symmetry > EQ_SYMM .and. dabs(X(1)) < dX) imin = -1
|
||||
if(Symmetry > EQ_SYMM .and. dabs(Y(1)) < dY) jmin = -1
|
||||
|
||||
SoA(1) = SYM1
|
||||
SoA(2) = SYM2
|
||||
SoA(3) = SYM3
|
||||
|
||||
call symmetry_bd(2,ex,f1,fh1,SoA)
|
||||
call symmetry_bd(2,ex,f2,fh2,SoA)
|
||||
|
||||
d12dx = ONE/F12/dX
|
||||
d12dy = ONE/F12/dY
|
||||
d12dz = ONE/F12/dZ
|
||||
|
||||
d2dx = ONE/TWO/dX
|
||||
d2dy = ONE/TWO/dY
|
||||
d2dz = ONE/TWO/dZ
|
||||
|
||||
f1x = ZEO; f1y = ZEO; f1z = ZEO
|
||||
f2x = ZEO; f2y = ZEO; f2z = ZEO
|
||||
|
||||
do k=1,ex(3)-1
|
||||
do j=1,ex(2)-1
|
||||
do i=1,ex(1)-1
|
||||
if(i+2 <= imax .and. i-2 >= imin .and. &
|
||||
j+2 <= jmax .and. j-2 >= jmin .and. &
|
||||
k+2 <= kmax .and. k-2 >= kmin) then
|
||||
f1x(i,j,k)=d12dx*(fh1(i-2,j,k)-EIT*fh1(i-1,j,k)+EIT*fh1(i+1,j,k)-fh1(i+2,j,k))
|
||||
f1y(i,j,k)=d12dy*(fh1(i,j-2,k)-EIT*fh1(i,j-1,k)+EIT*fh1(i,j+1,k)-fh1(i,j+2,k))
|
||||
f1z(i,j,k)=d12dz*(fh1(i,j,k-2)-EIT*fh1(i,j,k-1)+EIT*fh1(i,j,k+1)-fh1(i,j,k+2))
|
||||
|
||||
f2x(i,j,k)=d12dx*(fh2(i-2,j,k)-EIT*fh2(i-1,j,k)+EIT*fh2(i+1,j,k)-fh2(i+2,j,k))
|
||||
f2y(i,j,k)=d12dy*(fh2(i,j-2,k)-EIT*fh2(i,j-1,k)+EIT*fh2(i,j+1,k)-fh2(i,j+2,k))
|
||||
f2z(i,j,k)=d12dz*(fh2(i,j,k-2)-EIT*fh2(i,j,k-1)+EIT*fh2(i,j,k+1)-fh2(i,j,k+2))
|
||||
elseif(i+1 <= imax .and. i-1 >= imin .and. &
|
||||
j+1 <= jmax .and. j-1 >= jmin .and. &
|
||||
k+1 <= kmax .and. k-1 >= kmin) then
|
||||
f1x(i,j,k)=d2dx*(-fh1(i-1,j,k)+fh1(i+1,j,k))
|
||||
f1y(i,j,k)=d2dy*(-fh1(i,j-1,k)+fh1(i,j+1,k))
|
||||
f1z(i,j,k)=d2dz*(-fh1(i,j,k-1)+fh1(i,j,k+1))
|
||||
|
||||
f2x(i,j,k)=d2dx*(-fh2(i-1,j,k)+fh2(i+1,j,k))
|
||||
f2y(i,j,k)=d2dy*(-fh2(i,j-1,k)+fh2(i,j+1,k))
|
||||
f2z(i,j,k)=d2dz*(-fh2(i,j,k-1)+fh2(i,j,k+1))
|
||||
endif
|
||||
enddo
|
||||
enddo
|
||||
enddo
|
||||
|
||||
return
|
||||
|
||||
end subroutine fderivs_batch2
|
||||
|
||||
#elif (ghost_width == 4)
|
||||
! sixth order code
|
||||
@@ -2380,9 +2077,6 @@
|
||||
|
||||
end subroutine fderivs
|
||||
!-----------------------------------------------------------------------------
|
||||
! batch first derivatives (4 fields), same symmetry setup
|
||||
!-----------------------------------------------------------------------------
|
||||
!-----------------------------------------------------------------------------
|
||||
!
|
||||
! single derivatives dx
|
||||
!
|
||||
|
||||
@@ -17,50 +17,62 @@
|
||||
real*8, dimension(ex(1),ex(2),ex(3)), intent(inout) :: Axx,Axy,Axz
|
||||
real*8, dimension(ex(1),ex(2),ex(3)), intent(inout) :: Ayy,Ayz,Azz
|
||||
|
||||
!~~~~~~~> Local variable:
|
||||
|
||||
real*8, dimension(ex(1),ex(2),ex(3)) :: trA,detg
|
||||
real*8, dimension(ex(1),ex(2),ex(3)) :: gxx,gyy,gzz
|
||||
real*8, dimension(ex(1),ex(2),ex(3)) :: gupxx,gupxy,gupxz,gupyy,gupyz,gupzz
|
||||
real*8, parameter :: F1o3 = 1.D0 / 3.D0, ONE = 1.D0, TWO = 2.D0
|
||||
|
||||
!~~~~~~>
|
||||
|
||||
gxx = dxx + ONE
|
||||
gyy = dyy + ONE
|
||||
gzz = dzz + ONE
|
||||
|
||||
detg = gxx * gyy * gzz + gxy * gyz * gxz + gxz * gxy * gyz - &
|
||||
gxz * gyy * gxz - gxy * gxy * gzz - gxx * gyz * gyz
|
||||
gupxx = ( gyy * gzz - gyz * gyz ) / detg
|
||||
gupxy = - ( gxy * gzz - gyz * gxz ) / detg
|
||||
gupxz = ( gxy * gyz - gyy * gxz ) / detg
|
||||
gupyy = ( gxx * gzz - gxz * gxz ) / detg
|
||||
gupyz = - ( gxx * gyz - gxy * gxz ) / detg
|
||||
gupzz = ( gxx * gyy - gxy * gxy ) / detg
|
||||
|
||||
trA = gupxx * Axx + gupyy * Ayy + gupzz * Azz &
|
||||
+ TWO * (gupxy * Axy + gupxz * Axz + gupyz * Ayz)
|
||||
|
||||
Axx = Axx - F1o3 * gxx * trA
|
||||
Axy = Axy - F1o3 * gxy * trA
|
||||
Axz = Axz - F1o3 * gxz * trA
|
||||
Ayy = Ayy - F1o3 * gyy * trA
|
||||
Ayz = Ayz - F1o3 * gyz * trA
|
||||
Azz = Azz - F1o3 * gzz * trA
|
||||
|
||||
detg = ONE / ( detg ** F1o3 )
|
||||
|
||||
gxx = gxx * detg
|
||||
gxy = gxy * detg
|
||||
gxz = gxz * detg
|
||||
gyy = gyy * detg
|
||||
gyz = gyz * detg
|
||||
gzz = gzz * detg
|
||||
|
||||
dxx = gxx - ONE
|
||||
dyy = gyy - ONE
|
||||
dzz = gzz - ONE
|
||||
!~~~~~~~> Local variable:
|
||||
|
||||
integer :: i,j,k
|
||||
real*8 :: lgxx,lgyy,lgzz,ldetg
|
||||
real*8 :: lgupxx,lgupxy,lgupxz,lgupyy,lgupyz,lgupzz
|
||||
real*8 :: ltrA,lscale
|
||||
real*8, parameter :: F1o3 = 1.D0 / 3.D0, ONE = 1.D0, TWO = 2.D0
|
||||
|
||||
!~~~~~~>
|
||||
|
||||
do k=1,ex(3)
|
||||
do j=1,ex(2)
|
||||
do i=1,ex(1)
|
||||
|
||||
lgxx = dxx(i,j,k) + ONE
|
||||
lgyy = dyy(i,j,k) + ONE
|
||||
lgzz = dzz(i,j,k) + ONE
|
||||
|
||||
ldetg = lgxx * lgyy * lgzz &
|
||||
+ gxy(i,j,k) * gyz(i,j,k) * gxz(i,j,k) &
|
||||
+ gxz(i,j,k) * gxy(i,j,k) * gyz(i,j,k) &
|
||||
- gxz(i,j,k) * lgyy * gxz(i,j,k) &
|
||||
- gxy(i,j,k) * gxy(i,j,k) * lgzz &
|
||||
- lgxx * gyz(i,j,k) * gyz(i,j,k)
|
||||
|
||||
lgupxx = ( lgyy * lgzz - gyz(i,j,k) * gyz(i,j,k) ) / ldetg
|
||||
lgupxy = - ( gxy(i,j,k) * lgzz - gyz(i,j,k) * gxz(i,j,k) ) / ldetg
|
||||
lgupxz = ( gxy(i,j,k) * gyz(i,j,k) - lgyy * gxz(i,j,k) ) / ldetg
|
||||
lgupyy = ( lgxx * lgzz - gxz(i,j,k) * gxz(i,j,k) ) / ldetg
|
||||
lgupyz = - ( lgxx * gyz(i,j,k) - gxy(i,j,k) * gxz(i,j,k) ) / ldetg
|
||||
lgupzz = ( lgxx * lgyy - gxy(i,j,k) * gxy(i,j,k) ) / ldetg
|
||||
|
||||
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 * gxy(i,j,k) * ltrA
|
||||
Axz(i,j,k) = Axz(i,j,k) - F1o3 * gxz(i,j,k) * ltrA
|
||||
Ayy(i,j,k) = Ayy(i,j,k) - F1o3 * lgyy * ltrA
|
||||
Ayz(i,j,k) = Ayz(i,j,k) - F1o3 * gyz(i,j,k) * ltrA
|
||||
Azz(i,j,k) = Azz(i,j,k) - F1o3 * lgzz * ltrA
|
||||
|
||||
lscale = ONE / ( ldetg ** F1o3 )
|
||||
|
||||
dxx(i,j,k) = lgxx * lscale - ONE
|
||||
gxy(i,j,k) = gxy(i,j,k) * lscale
|
||||
gxz(i,j,k) = gxz(i,j,k) * lscale
|
||||
dyy(i,j,k) = lgyy * lscale - ONE
|
||||
gyz(i,j,k) = gyz(i,j,k) * lscale
|
||||
dzz(i,j,k) = lgzz * lscale - ONE
|
||||
|
||||
enddo
|
||||
enddo
|
||||
enddo
|
||||
|
||||
return
|
||||
|
||||
@@ -81,52 +93,72 @@
|
||||
real*8, dimension(ex(1),ex(2),ex(3)), intent(inout) :: Axx,Axy,Axz
|
||||
real*8, dimension(ex(1),ex(2),ex(3)), intent(inout) :: Ayy,Ayz,Azz
|
||||
|
||||
!~~~~~~~> Local variable:
|
||||
|
||||
real*8, dimension(ex(1),ex(2),ex(3)) :: trA
|
||||
real*8, dimension(ex(1),ex(2),ex(3)) :: gxx,gyy,gzz
|
||||
real*8, dimension(ex(1),ex(2),ex(3)) :: gupxx,gupxy,gupxz,gupyy,gupyz,gupzz
|
||||
real*8, parameter :: F1o3 = 1.D0 / 3.D0, ONE = 1.D0, TWO = 2.D0
|
||||
|
||||
!~~~~~~>
|
||||
|
||||
gxx = dxx + ONE
|
||||
gyy = dyy + ONE
|
||||
gzz = dzz + ONE
|
||||
! for g
|
||||
gupzz = gxx * gyy * gzz + gxy * gyz * gxz + gxz * gxy * gyz - &
|
||||
gxz * gyy * gxz - gxy * gxy * gzz - gxx * gyz * gyz
|
||||
|
||||
gupzz = ONE / ( gupzz ** F1o3 )
|
||||
|
||||
gxx = gxx * gupzz
|
||||
gxy = gxy * gupzz
|
||||
gxz = gxz * gupzz
|
||||
gyy = gyy * gupzz
|
||||
gyz = gyz * gupzz
|
||||
gzz = gzz * gupzz
|
||||
|
||||
dxx = gxx - ONE
|
||||
dyy = gyy - ONE
|
||||
dzz = gzz - ONE
|
||||
! for A
|
||||
|
||||
gupxx = ( gyy * gzz - gyz * gyz )
|
||||
gupxy = - ( gxy * gzz - gyz * gxz )
|
||||
gupxz = ( gxy * gyz - gyy * gxz )
|
||||
gupyy = ( gxx * gzz - gxz * gxz )
|
||||
gupyz = - ( gxx * gyz - gxy * gxz )
|
||||
gupzz = ( gxx * gyy - gxy * gxy )
|
||||
|
||||
trA = gupxx * Axx + gupyy * Ayy + gupzz * Azz &
|
||||
+ TWO * (gupxy * Axy + gupxz * Axz + gupyz * Ayz)
|
||||
|
||||
Axx = Axx - F1o3 * gxx * trA
|
||||
Axy = Axy - F1o3 * gxy * trA
|
||||
Axz = Axz - F1o3 * gxz * trA
|
||||
Ayy = Ayy - F1o3 * gyy * trA
|
||||
Ayz = Ayz - F1o3 * gyz * trA
|
||||
Azz = Azz - F1o3 * gzz * trA
|
||||
!~~~~~~~> Local variable:
|
||||
|
||||
integer :: i,j,k
|
||||
real*8 :: lgxx,lgyy,lgzz,lscale
|
||||
real*8 :: lgxy,lgxz,lgyz
|
||||
real*8 :: lgupxx,lgupxy,lgupxz,lgupyy,lgupyz,lgupzz
|
||||
real*8 :: ltrA
|
||||
real*8, parameter :: F1o3 = 1.D0 / 3.D0, ONE = 1.D0, TWO = 2.D0
|
||||
|
||||
!~~~~~~>
|
||||
|
||||
do k=1,ex(3)
|
||||
do j=1,ex(2)
|
||||
do i=1,ex(1)
|
||||
|
||||
! 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)
|
||||
|
||||
lscale = lgxx * lgyy * lgzz + lgxy * lgyz * lgxz &
|
||||
+ lgxz * lgxy * lgyz - lgxz * lgyy * lgxz &
|
||||
- lgxy * lgxy * lgzz - lgxx * lgyz * lgyz
|
||||
|
||||
lscale = ONE / ( lscale ** F1o3 )
|
||||
|
||||
lgxx = lgxx * lscale
|
||||
lgxy = lgxy * lscale
|
||||
lgxz = lgxz * lscale
|
||||
lgyy = lgyy * lscale
|
||||
lgyz = lgyz * lscale
|
||||
lgzz = lgzz * lscale
|
||||
|
||||
dxx(i,j,k) = lgxx - ONE
|
||||
gxy(i,j,k) = lgxy
|
||||
gxz(i,j,k) = lgxz
|
||||
dyy(i,j,k) = lgyy - ONE
|
||||
gyz(i,j,k) = lgyz
|
||||
dzz(i,j,k) = lgzz - ONE
|
||||
|
||||
! for A: trace-free using normalized metric (det=1, no division needed)
|
||||
lgupxx = ( lgyy * lgzz - lgyz * lgyz )
|
||||
lgupxy = - ( lgxy * lgzz - lgyz * lgxz )
|
||||
lgupxz = ( lgxy * lgyz - lgyy * lgxz )
|
||||
lgupyy = ( lgxx * lgzz - lgxz * lgxz )
|
||||
lgupyz = - ( lgxx * lgyz - lgxy * lgxz )
|
||||
lgupzz = ( lgxx * lgyy - lgxy * lgxy )
|
||||
|
||||
ltrA = lgupxx * Axx(i,j,k) + lgupyy * Ayy(i,j,k) &
|
||||
+ lgupzz * Azz(i,j,k) &
|
||||
+ TWO * (lgupxy * Axy(i,j,k) + lgupxz * Axz(i,j,k) &
|
||||
+ lgupyz * Ayz(i,j,k))
|
||||
|
||||
Axx(i,j,k) = Axx(i,j,k) - F1o3 * lgxx * ltrA
|
||||
Axy(i,j,k) = Axy(i,j,k) - F1o3 * lgxy * ltrA
|
||||
Axz(i,j,k) = Axz(i,j,k) - F1o3 * lgxz * ltrA
|
||||
Ayy(i,j,k) = Ayy(i,j,k) - F1o3 * lgyy * ltrA
|
||||
Ayz(i,j,k) = Ayz(i,j,k) - F1o3 * lgyz * ltrA
|
||||
Azz(i,j,k) = Azz(i,j,k) - F1o3 * lgzz * ltrA
|
||||
|
||||
enddo
|
||||
enddo
|
||||
enddo
|
||||
|
||||
return
|
||||
|
||||
|
||||
@@ -324,8 +324,7 @@ subroutine symmetry_bd(ord,extc,func,funcc,SoA)
|
||||
|
||||
integer::i
|
||||
|
||||
funcc = 0.d0
|
||||
funcc(1:extc(1),1:extc(2),1:extc(3)) = func
|
||||
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)
|
||||
enddo
|
||||
@@ -350,8 +349,7 @@ subroutine symmetry_tbd(ord,extc,func,funcc,SoA)
|
||||
|
||||
integer::i
|
||||
|
||||
funcc = 0.d0
|
||||
funcc(1:extc(1),1:extc(2),1:extc(3)) = func
|
||||
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)
|
||||
funcc(extc(1)+1+i,1:extc(2),1:extc(3)) = funcc(extc(1)-1-i,1:extc(2),1:extc(3))*SoA(1)
|
||||
@@ -379,8 +377,7 @@ subroutine symmetry_stbd(ord,extc,func,funcc,SoA)
|
||||
|
||||
integer::i
|
||||
|
||||
funcc = 0.d0
|
||||
funcc(1:extc(1),1:extc(2),1:extc(3)) = func
|
||||
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)
|
||||
funcc(extc(1)+1+i,1:extc(2),1:extc(3)) = funcc(extc(1)-1-i,1:extc(2),1:extc(3))*SoA(1)
|
||||
@@ -886,17 +883,20 @@ 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+1,1:extc(2),1:extc(3))*SoA(1)
|
||||
enddo
|
||||
do i=0,ord-1
|
||||
funcc(:,-i,1:extc(3)) = funcc(:,i+1,1:extc(3))*SoA(2)
|
||||
enddo
|
||||
do i=0,ord-1
|
||||
funcc(:,:,-i) = funcc(:,:,i+1)*SoA(3)
|
||||
enddo
|
||||
!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
|
||||
|
||||
end subroutine symmetry_bd
|
||||
|
||||
@@ -912,8 +912,7 @@ subroutine symmetry_tbd(ord,extc,func,funcc,SoA)
|
||||
|
||||
integer::i
|
||||
|
||||
funcc = 0.d0
|
||||
funcc(1:extc(1),1:extc(2),1:extc(3)) = func
|
||||
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)
|
||||
funcc(extc(1)+1+i,1:extc(2),1:extc(3)) = funcc(extc(1)-i,1:extc(2),1:extc(3))*SoA(1)
|
||||
@@ -941,8 +940,7 @@ subroutine symmetry_stbd(ord,extc,func,funcc,SoA)
|
||||
|
||||
integer::i
|
||||
|
||||
funcc = 0.d0
|
||||
funcc(1:extc(1),1:extc(2),1:extc(3)) = func
|
||||
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)
|
||||
funcc(extc(1)+1+i,1:extc(2),1:extc(3)) = funcc(extc(1)-i,1:extc(2),1:extc(3))*SoA(1)
|
||||
@@ -1113,153 +1111,355 @@ end subroutine d2dump
|
||||
!~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
!~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
!~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
! common code for cell and vertex
|
||||
!------------------------------------------------------------------------------
|
||||
! Lagrangian polynomial interpolation
|
||||
!------------------------------------------------------------------------------
|
||||
|
||||
subroutine polint(xa,ya,x,y,dy,ordn)
|
||||
|
||||
implicit none
|
||||
|
||||
!~~~~~~> Input Parameter:
|
||||
integer,intent(in) :: ordn
|
||||
real*8, dimension(ordn), intent(in) :: xa,ya
|
||||
real*8, intent(in) :: x
|
||||
real*8, intent(out) :: y,dy
|
||||
|
||||
!~~~~~~> Other parameter:
|
||||
|
||||
integer :: m,n,ns
|
||||
real*8, dimension(ordn) :: c,d,den,ho
|
||||
real*8 :: dif,dift
|
||||
|
||||
!~~~~~~>
|
||||
|
||||
n=ordn
|
||||
m=ordn
|
||||
|
||||
c=ya
|
||||
d=ya
|
||||
ho=xa-x
|
||||
|
||||
ns=1
|
||||
dif=abs(x-xa(1))
|
||||
do m=1,n
|
||||
dift=abs(x-xa(m))
|
||||
if(dift < dif) then
|
||||
ns=m
|
||||
dif=dift
|
||||
end if
|
||||
end do
|
||||
|
||||
y=ya(ns)
|
||||
ns=ns-1
|
||||
do m=1,n-1
|
||||
den(1:n-m)=ho(1:n-m)-ho(1+m:n)
|
||||
if (any(den(1:n-m) == 0.0))then
|
||||
write(*,*) 'failure in polint for point',x
|
||||
write(*,*) 'with input points: ',xa
|
||||
stop
|
||||
endif
|
||||
den(1:n-m)=(c(2:n-m+1)-d(1:n-m))/den(1:n-m)
|
||||
d(1:n-m)=ho(1+m:n)*den(1:n-m)
|
||||
c(1:n-m)=ho(1:n-m)*den(1:n-m)
|
||||
if (2*ns < n-m) then
|
||||
dy=c(ns+1)
|
||||
else
|
||||
dy=d(ns)
|
||||
ns=ns-1
|
||||
end if
|
||||
y=y+dy
|
||||
end do
|
||||
|
||||
return
|
||||
|
||||
end subroutine polint
|
||||
!------------------------------------------------------------------------------
|
||||
!
|
||||
! interpolation in 2 dimensions, follow yx order
|
||||
!
|
||||
!------------------------------------------------------------------------------
|
||||
subroutine polin2(x1a,x2a,ya,x1,x2,y,dy,ordn)
|
||||
|
||||
implicit none
|
||||
|
||||
!~~~~~~> Input parameters:
|
||||
integer,intent(in) :: ordn
|
||||
real*8, dimension(1:ordn), intent(in) :: x1a,x2a
|
||||
real*8, dimension(1:ordn,1:ordn), intent(in) :: ya
|
||||
real*8, intent(in) :: x1,x2
|
||||
real*8, intent(out) :: y,dy
|
||||
|
||||
!~~~~~~> Other parameters:
|
||||
|
||||
integer :: i,m
|
||||
real*8, dimension(ordn) :: ymtmp
|
||||
real*8, dimension(ordn) :: yntmp
|
||||
|
||||
m=size(x1a)
|
||||
|
||||
do i=1,m
|
||||
|
||||
yntmp=ya(i,:)
|
||||
call polint(x2a,yntmp,x2,ymtmp(i),dy,ordn)
|
||||
|
||||
end do
|
||||
|
||||
call polint(x1a,ymtmp,x1,y,dy,ordn)
|
||||
|
||||
return
|
||||
|
||||
end subroutine polin2
|
||||
!------------------------------------------------------------------------------
|
||||
!
|
||||
! interpolation in 3 dimensions, follow zyx order
|
||||
!
|
||||
!------------------------------------------------------------------------------
|
||||
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:
|
||||
|
||||
integer :: i,j,m,n
|
||||
real*8, dimension(ordn,ordn) :: yatmp
|
||||
real*8, dimension(ordn) :: ymtmp
|
||||
real*8, dimension(ordn) :: yntmp
|
||||
real*8, dimension(ordn) :: yqtmp
|
||||
|
||||
m=size(x1a)
|
||||
n=size(x2a)
|
||||
|
||||
do i=1,m
|
||||
do j=1,n
|
||||
|
||||
yqtmp=ya(i,j,:)
|
||||
call polint(x3a,yqtmp,x3,yatmp(i,j),dy,ordn)
|
||||
|
||||
end do
|
||||
|
||||
yntmp=yatmp(i,:)
|
||||
call polint(x2a,yntmp,x2,ymtmp(i),dy,ordn)
|
||||
|
||||
end do
|
||||
|
||||
call polint(x1a,ymtmp,x1,y,dy,ordn)
|
||||
|
||||
return
|
||||
|
||||
end subroutine polin3
|
||||
! common code for cell and vertex
|
||||
!------------------------------------------------------------------------------
|
||||
! Lagrangian polynomial interpolation
|
||||
!------------------------------------------------------------------------------
|
||||
#ifndef POLINT6_USE_BARYCENTRIC
|
||||
#define POLINT6_USE_BARYCENTRIC 1
|
||||
#endif
|
||||
|
||||
!DIR$ ATTRIBUTES FORCEINLINE :: polint6_neville
|
||||
subroutine polint6_neville(xa, ya, x, y, dy)
|
||||
implicit none
|
||||
|
||||
real*8, dimension(6), intent(in) :: xa, ya
|
||||
real*8, intent(in) :: x
|
||||
real*8, intent(out) :: y, dy
|
||||
|
||||
integer :: i, m, ns, n_m
|
||||
real*8, dimension(6) :: c, d, ho
|
||||
real*8 :: dif, dift, hp, h, den_val
|
||||
|
||||
c = ya
|
||||
d = ya
|
||||
ho = xa - x
|
||||
|
||||
ns = 1
|
||||
dif = abs(x - xa(1))
|
||||
|
||||
do i = 2, 6
|
||||
dift = abs(x - xa(i))
|
||||
if (dift < dif) then
|
||||
ns = i
|
||||
dif = dift
|
||||
end if
|
||||
end do
|
||||
|
||||
y = ya(ns)
|
||||
ns = ns - 1
|
||||
|
||||
do m = 1, 5
|
||||
n_m = 6 - m
|
||||
do i = 1, n_m
|
||||
hp = ho(i)
|
||||
h = ho(i+m)
|
||||
den_val = hp - h
|
||||
|
||||
if (den_val == 0.0d0) then
|
||||
write(*,*) 'failure in polint for point',x
|
||||
write(*,*) 'with input points: ',xa
|
||||
stop
|
||||
end if
|
||||
|
||||
den_val = (c(i+1) - d(i)) / den_val
|
||||
|
||||
d(i) = h * den_val
|
||||
c(i) = hp * den_val
|
||||
end do
|
||||
|
||||
if (2 * ns < n_m) then
|
||||
dy = c(ns + 1)
|
||||
else
|
||||
dy = d(ns)
|
||||
ns = ns - 1
|
||||
end if
|
||||
y = y + dy
|
||||
end do
|
||||
|
||||
return
|
||||
end subroutine polint6_neville
|
||||
|
||||
!DIR$ ATTRIBUTES FORCEINLINE :: polint6_barycentric
|
||||
subroutine polint6_barycentric(xa, ya, x, y, dy)
|
||||
implicit none
|
||||
|
||||
real*8, dimension(6), intent(in) :: xa, ya
|
||||
real*8, intent(in) :: x
|
||||
real*8, intent(out) :: y, dy
|
||||
|
||||
integer :: i, j
|
||||
logical :: is_uniform
|
||||
real*8, dimension(6) :: lambda
|
||||
real*8 :: dx, den_i, term, num, den, step, tol
|
||||
real*8, parameter :: c_uniform(6) = (/ -1.d0, 5.d0, -10.d0, 10.d0, -5.d0, 1.d0 /)
|
||||
|
||||
do i = 1, 6
|
||||
if (x == xa(i)) then
|
||||
y = ya(i)
|
||||
dy = 0.d0
|
||||
return
|
||||
end if
|
||||
end do
|
||||
|
||||
step = xa(2) - xa(1)
|
||||
is_uniform = (step /= 0.d0)
|
||||
if (is_uniform) then
|
||||
tol = 64.d0 * epsilon(1.d0) * max(1.d0, abs(step))
|
||||
do i = 3, 6
|
||||
if (abs((xa(i) - xa(i-1)) - step) > tol) then
|
||||
is_uniform = .false.
|
||||
exit
|
||||
end if
|
||||
end do
|
||||
end if
|
||||
|
||||
if (is_uniform) then
|
||||
num = 0.d0
|
||||
den = 0.d0
|
||||
do i = 1, 6
|
||||
term = c_uniform(i) / (x - xa(i))
|
||||
num = num + term * ya(i)
|
||||
den = den + term
|
||||
end do
|
||||
y = num / den
|
||||
dy = 0.d0
|
||||
return
|
||||
end if
|
||||
|
||||
do i = 1, 6
|
||||
den_i = 1.d0
|
||||
do j = 1, 6
|
||||
if (j /= i) then
|
||||
dx = xa(i) - xa(j)
|
||||
if (dx == 0.0d0) then
|
||||
write(*,*) 'failure in polint for point',x
|
||||
write(*,*) 'with input points: ',xa
|
||||
stop
|
||||
end if
|
||||
den_i = den_i * dx
|
||||
end if
|
||||
end do
|
||||
lambda(i) = 1.d0 / den_i
|
||||
end do
|
||||
|
||||
num = 0.d0
|
||||
den = 0.d0
|
||||
do i = 1, 6
|
||||
term = lambda(i) / (x - xa(i))
|
||||
num = num + term * ya(i)
|
||||
den = den + term
|
||||
end do
|
||||
|
||||
y = num / den
|
||||
dy = 0.d0
|
||||
|
||||
return
|
||||
end subroutine polint6_barycentric
|
||||
|
||||
!DIR$ ATTRIBUTES FORCEINLINE :: polint
|
||||
subroutine polint(xa, ya, x, y, dy, ordn)
|
||||
implicit none
|
||||
|
||||
integer, intent(in) :: ordn
|
||||
real*8, dimension(ordn), intent(in) :: xa, ya
|
||||
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
|
||||
|
||||
integer,intent(in) :: ordn
|
||||
real*8, dimension(1:ordn), intent(in) :: x1a,x2a
|
||||
real*8, dimension(1:ordn,1:ordn), intent(in) :: ya
|
||||
real*8, intent(in) :: x1,x2
|
||||
real*8, intent(out) :: y,dy
|
||||
|
||||
#ifdef POLINT_LEGACY_ORDER
|
||||
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
|
||||
!------------------------------------------------------------------------------
|
||||
!
|
||||
! interpolation in 3 dimensions, follow zyx order
|
||||
!
|
||||
!------------------------------------------------------------------------------
|
||||
subroutine polin3(x1a,x2a,x3a,ya,x1,x2,x3,y,dy,ordn)
|
||||
implicit none
|
||||
|
||||
integer,intent(in) :: ordn
|
||||
real*8, dimension(1:ordn), intent(in) :: x1a,x2a,x3a
|
||||
real*8, dimension(1:ordn,1:ordn,1:ordn), intent(in) :: ya
|
||||
real*8, intent(in) :: x1,x2,x3
|
||||
real*8, intent(out) :: y,dy
|
||||
|
||||
#ifdef POLINT_LEGACY_ORDER
|
||||
integer :: i,j,m,n
|
||||
real*8, dimension(ordn,ordn) :: yatmp
|
||||
real*8, dimension(ordn) :: ymtmp
|
||||
real*8, dimension(ordn) :: yntmp
|
||||
real*8, dimension(ordn) :: yqtmp
|
||||
|
||||
m=size(x1a)
|
||||
n=size(x2a)
|
||||
do i=1,m
|
||||
do j=1,n
|
||||
yqtmp=ya(i,j,:)
|
||||
call polint(x3a,yqtmp,x3,yatmp(i,j),dy,ordn)
|
||||
end do
|
||||
yntmp=yatmp(i,:)
|
||||
call polint(x2a,yntmp,x2,ymtmp(i),dy,ordn)
|
||||
end do
|
||||
call polint(x1a,ymtmp,x1,y,dy,ordn)
|
||||
#else
|
||||
integer :: i, j, k
|
||||
real*8, dimension(ordn) :: w1, w2
|
||||
real*8, dimension(ordn) :: ymtmp
|
||||
real*8 :: yx_sum, x_sum
|
||||
|
||||
call polint_lagrange_weights(x1a, x1, w1, ordn)
|
||||
call polint_lagrange_weights(x2a, x2, w2, ordn)
|
||||
|
||||
do k = 1, ordn
|
||||
yx_sum = 0.d0
|
||||
do j = 1, ordn
|
||||
x_sum = 0.d0
|
||||
do i = 1, ordn
|
||||
x_sum = x_sum + w1(i) * ya(i,j,k)
|
||||
end do
|
||||
yx_sum = yx_sum + w2(j) * x_sum
|
||||
end do
|
||||
ymtmp(k) = yx_sum
|
||||
end do
|
||||
|
||||
call polint(x3a, ymtmp, x3, y, dy, ordn)
|
||||
#endif
|
||||
|
||||
return
|
||||
end subroutine polin3
|
||||
!--------------------------------------------------------------------------------------
|
||||
! calculate L2norm
|
||||
! calculate L2norm
|
||||
subroutine l2normhelper(ex, X, Y, Z,xmin,ymin,zmin,xmax,ymax,zmax,&
|
||||
f,f_out,gw)
|
||||
|
||||
@@ -1276,9 +1476,9 @@ end subroutine d2dump
|
||||
real*8 :: dX, dY, dZ
|
||||
integer::imin,jmin,kmin
|
||||
integer::imax,jmax,kmax
|
||||
integer::i,j,k,n_elements
|
||||
real*8, dimension(:), allocatable :: f_flat
|
||||
real*8, external :: DDOT
|
||||
integer::i,j,k,n_elements
|
||||
real*8, dimension(:), allocatable :: f_flat
|
||||
real*8, external :: DDOT
|
||||
|
||||
dX = X(2) - X(1)
|
||||
dY = Y(2) - Y(1)
|
||||
@@ -1302,20 +1502,91 @@ if(dabs(X(1)-xmin) < dX) imin = 1
|
||||
if(dabs(Y(1)-ymin) < dY) jmin = 1
|
||||
if(dabs(Z(1)-zmin) < dZ) kmin = 1
|
||||
|
||||
! Optimized with oneMKL BLAS DDOT for dot product
|
||||
n_elements = (imax-imin+1)*(jmax-jmin+1)*(kmax-kmin+1)
|
||||
allocate(f_flat(n_elements))
|
||||
f_flat = reshape(f(imin:imax,jmin:jmax,kmin:kmax), [n_elements])
|
||||
f_out = DDOT(n_elements, f_flat, 1, f_flat, 1)
|
||||
deallocate(f_flat)
|
||||
n_elements = (imax-imin+1)*(jmax-jmin+1)*(kmax-kmin+1)
|
||||
allocate(f_flat(n_elements))
|
||||
f_flat = reshape(f(imin:imax,jmin:jmax,kmin:kmax), [n_elements])
|
||||
f_out = DDOT(n_elements, f_flat, 1, f_flat, 1)
|
||||
deallocate(f_flat)
|
||||
|
||||
f_out = f_out*dX*dY*dZ
|
||||
|
||||
return
|
||||
|
||||
end subroutine l2normhelper
|
||||
!--------------------------------------------------------------------------------------
|
||||
! calculate L2norm especially for shell Blocks
|
||||
!--------------------------------------------------------------------------------------
|
||||
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,&
|
||||
f,f_out,gw,ogw,Symmetry)
|
||||
|
||||
@@ -1332,9 +1603,9 @@ f_out = f_out*dX*dY*dZ
|
||||
real*8 :: dX, dY, dZ
|
||||
integer::imin,jmin,kmin
|
||||
integer::imax,jmax,kmax
|
||||
integer::i,j,k,n_elements
|
||||
real*8, dimension(:), allocatable :: f_flat
|
||||
real*8, external :: DDOT
|
||||
integer::i,j,k,n_elements
|
||||
real*8, dimension(:), allocatable :: f_flat
|
||||
real*8, external :: DDOT
|
||||
|
||||
real*8 :: PIo4
|
||||
|
||||
@@ -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)
|
||||
allocate(f_flat(n_elements))
|
||||
f_flat = reshape(f(imin:imax,jmin:jmax,kmin:kmax), [n_elements])
|
||||
f_out = DDOT(n_elements, f_flat, 1, f_flat, 1)
|
||||
deallocate(f_flat)
|
||||
n_elements = (imax-imin+1)*(jmax-jmin+1)*(kmax-kmin+1)
|
||||
allocate(f_flat(n_elements))
|
||||
f_flat = reshape(f(imin:imax,jmin:jmax,kmin:kmax), [n_elements])
|
||||
f_out = DDOT(n_elements, f_flat, 1, f_flat, 1)
|
||||
deallocate(f_flat)
|
||||
|
||||
f_out = f_out*dX*dY*dZ
|
||||
|
||||
@@ -1429,9 +1699,9 @@ f_out = f_out*dX*dY*dZ
|
||||
real*8 :: dX, dY, dZ
|
||||
integer::imin,jmin,kmin
|
||||
integer::imax,jmax,kmax
|
||||
integer::i,j,k
|
||||
real*8, dimension(:), allocatable :: f_flat
|
||||
real*8, external :: DDOT
|
||||
integer::i,j,k
|
||||
real*8, dimension(:), allocatable :: f_flat
|
||||
real*8, external :: DDOT
|
||||
|
||||
real*8 :: PIo4
|
||||
|
||||
@@ -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))
|
||||
f_flat = reshape(f(imin:imax,jmin:jmax,kmin:kmax), [Nout])
|
||||
f_out = DDOT(Nout, f_flat, 1, f_flat, 1)
|
||||
deallocate(f_flat)
|
||||
Nout = (imax-imin+1)*(jmax-jmin+1)*(kmax-kmin+1)
|
||||
allocate(f_flat(Nout))
|
||||
f_flat = reshape(f(imin:imax,jmin:jmax,kmin:kmax), [Nout])
|
||||
f_out = DDOT(Nout, f_flat, 1, f_flat, 1)
|
||||
deallocate(f_flat)
|
||||
|
||||
return
|
||||
|
||||
@@ -1600,9 +1869,12 @@ 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
|
||||
|
||||
fout = C1*f1+C2*f2+C3*f3
|
||||
real*8,parameter::C1=3.d0/8.d0,C2=3.d0/4.d0,C3=-1.d0/8.d0
|
||||
integer :: i,j,k
|
||||
|
||||
do concurrent (k=1:ext(3), j=1:ext(2), i=1:ext(1))
|
||||
fout(i,j,k) = C1*f1(i,j,k)+C2*f2(i,j,k)+C3*f3(i,j,k)
|
||||
end do
|
||||
|
||||
return
|
||||
|
||||
@@ -1696,8 +1968,8 @@ deallocate(f_flat)
|
||||
real*8, dimension(ORDN,ORDN,ORDN) :: ya
|
||||
real*8, dimension(ORDN,ORDN) :: tmp2
|
||||
real*8, dimension(ORDN) :: tmp1
|
||||
real*8, dimension(3) :: SoAh
|
||||
real*8, external :: DDOT
|
||||
real*8, dimension(3) :: SoAh
|
||||
real*8, external :: DDOT
|
||||
|
||||
! +1 because c++ gives 0 for first point
|
||||
cxB = inds+1
|
||||
@@ -1733,21 +2005,17 @@ deallocate(f_flat)
|
||||
ya=fh(cxB(1):cxT(1),cxB(2):cxT(2),cxB(3):cxT(3))
|
||||
endif
|
||||
|
||||
! Optimized with BLAS operations for better performance
|
||||
! First dimension: z-direction weighted sum
|
||||
tmp2=0
|
||||
do m=1,ORDN
|
||||
tmp2 = tmp2 + coef(2*ORDN+m)*ya(:,:,m)
|
||||
enddo
|
||||
|
||||
! Second dimension: y-direction weighted sum
|
||||
tmp1=0
|
||||
do m=1,ORDN
|
||||
tmp1 = tmp1 + coef(ORDN+m)*tmp2(:,m)
|
||||
enddo
|
||||
|
||||
! Third dimension: x-direction weighted sum using BLAS DDOT
|
||||
f_int = DDOT(ORDN, coef(1:ORDN), 1, tmp1, 1)
|
||||
f_int = DDOT(ORDN, coef(1:ORDN), 1, tmp1, 1)
|
||||
|
||||
return
|
||||
|
||||
@@ -1776,8 +2044,8 @@ deallocate(f_flat)
|
||||
integer,dimension(2) :: cxB,cxT
|
||||
real*8, dimension(ORDN,ORDN) :: ya
|
||||
real*8, dimension(ORDN) :: tmp1
|
||||
real*8, dimension(2) :: SoAh
|
||||
real*8, external :: DDOT
|
||||
real*8, dimension(2) :: SoAh
|
||||
real*8, external :: DDOT
|
||||
|
||||
! +1 because c++ gives 0 for first point
|
||||
cxB = inds(1:2)+1
|
||||
@@ -1807,14 +2075,12 @@ deallocate(f_flat)
|
||||
ya=fh(cxB(1):cxT(1),cxB(2):cxT(2),inds(3))
|
||||
endif
|
||||
|
||||
! Optimized with BLAS operations
|
||||
tmp1=0
|
||||
do m=1,ORDN
|
||||
tmp1 = tmp1 + coef(ORDN+m)*ya(:,m)
|
||||
enddo
|
||||
|
||||
! Use BLAS DDOT for final weighted sum
|
||||
f_int = DDOT(ORDN, coef(1:ORDN), 1, tmp1, 1)
|
||||
f_int = DDOT(ORDN, coef(1:ORDN), 1, tmp1, 1)
|
||||
|
||||
return
|
||||
|
||||
@@ -1840,12 +2106,12 @@ deallocate(f_flat)
|
||||
!~~~~~~> Other parameters:
|
||||
|
||||
real*8, dimension(-ORDN+1:ex(1)+ORDN,-ORDN+1:ex(2)+ORDN,ex(3)) :: fh
|
||||
integer :: m
|
||||
integer :: cxB,cxT
|
||||
real*8, dimension(ORDN) :: ya
|
||||
real*8 :: SoAh
|
||||
integer,dimension(3) :: inds
|
||||
real*8, external :: DDOT
|
||||
integer :: m
|
||||
integer :: cxB,cxT
|
||||
real*8, dimension(ORDN) :: ya
|
||||
real*8 :: SoAh
|
||||
integer,dimension(3) :: inds
|
||||
real*8, external :: DDOT
|
||||
|
||||
! +1 because c++ gives 0 for first point
|
||||
inds = indsi + 1
|
||||
@@ -1906,8 +2172,7 @@ deallocate(f_flat)
|
||||
write(*,*)"error in global_interpind1d, not recognized dumyd = ",dumyd
|
||||
endif
|
||||
|
||||
! Optimized with BLAS DDOT for weighted sum
|
||||
f_int = DDOT(ORDN, coef, 1, ya, 1)
|
||||
f_int = DDOT(ORDN, coef, 1, ya, 1)
|
||||
|
||||
return
|
||||
|
||||
@@ -2139,38 +2404,32 @@ deallocate(f_flat)
|
||||
|
||||
end function fWigner_d_function
|
||||
!----------------------------------
|
||||
! Optimized factorial function using lookup table for small N
|
||||
! and log-gamma for large N to avoid overflow
|
||||
function ffact(N) result(gont)
|
||||
implicit none
|
||||
integer,intent(in) :: N
|
||||
|
||||
real*8 :: gont
|
||||
integer :: i
|
||||
|
||||
! Lookup table for factorials 0! to 20! (precomputed)
|
||||
real*8, parameter, dimension(0:20) :: fact_table = [ &
|
||||
1.d0, 1.d0, 2.d0, 6.d0, 24.d0, 120.d0, 720.d0, 5040.d0, 40320.d0, &
|
||||
362880.d0, 3628800.d0, 39916800.d0, 479001600.d0, 6227020800.d0, &
|
||||
87178291200.d0, 1307674368000.d0, 20922789888000.d0, &
|
||||
355687428096000.d0, 6402373705728000.d0, 121645100408832000.d0, &
|
||||
2432902008176640000.d0 ]
|
||||
real*8 :: gont
|
||||
|
||||
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, &
|
||||
87178291200.d0, 1307674368000.d0, 20922789888000.d0, &
|
||||
355687428096000.d0, 6402373705728000.d0, 121645100408832000.d0, &
|
||||
2432902008176640000.d0 ]
|
||||
|
||||
! sanity check
|
||||
if(N < 0)then
|
||||
write(*,*) "ffact: error input for factorial"
|
||||
gont = 1.d0
|
||||
return
|
||||
endif
|
||||
|
||||
! Use lookup table for small N (fast path)
|
||||
if(N <= 20)then
|
||||
gont = fact_table(N)
|
||||
else
|
||||
! Use log-gamma function for large N: N! = exp(log_gamma(N+1))
|
||||
! This avoids overflow and is computed efficiently
|
||||
gont = exp(log_gamma(dble(N+1)))
|
||||
endif
|
||||
if(N < 0)then
|
||||
write(*,*) "ffact: error input for factorial"
|
||||
gont = 1.d0
|
||||
return
|
||||
endif
|
||||
|
||||
if(N <= 20)then
|
||||
gont = fact_table(N)
|
||||
else
|
||||
gont = exp(log_gamma(dble(N+1)))
|
||||
endif
|
||||
|
||||
return
|
||||
|
||||
|
||||
@@ -12,9 +12,10 @@
|
||||
#define f_global_interpind global_interpind
|
||||
#define f_global_interpind2d global_interpind2d
|
||||
#define f_global_interpind1d global_interpind1d
|
||||
#define f_l2normhelper l2normhelper
|
||||
#define f_l2normhelper_sh l2normhelper_sh
|
||||
#define f_l2normhelper_sh_rms l2normhelper_sh_rms
|
||||
#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
|
||||
#define f_average3 average3
|
||||
#define f_average2 average2
|
||||
@@ -41,9 +42,10 @@
|
||||
#define f_global_interpind GLOBAL_INTERPIND
|
||||
#define f_global_interpind2d GLOBAL_INTERPIND2D
|
||||
#define f_global_interpind1d GLOBAL_INTERPIND1D
|
||||
#define f_l2normhelper L2NORMHELPER
|
||||
#define f_l2normhelper_sh L2NORMHELPER_SH
|
||||
#define f_l2normhelper_sh_rms L2NORMHELPER_SH_RMS
|
||||
#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
|
||||
#define f_average3 AVERAGE3
|
||||
#define f_average2 AVERAGE2
|
||||
@@ -70,9 +72,10 @@
|
||||
#define f_global_interpind global_interpind_
|
||||
#define f_global_interpind2d global_interpind2d_
|
||||
#define f_global_interpind1d global_interpind1d_
|
||||
#define f_l2normhelper l2normhelper_
|
||||
#define f_l2normhelper_sh l2normhelper_sh_
|
||||
#define f_l2normhelper_sh_rms l2normhelper_sh_rms_
|
||||
#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_
|
||||
#define f_average3 average3_
|
||||
#define f_average2 average2_
|
||||
@@ -156,21 +159,30 @@ extern "C"
|
||||
int *, double *, int &, int &);
|
||||
}
|
||||
|
||||
extern "C"
|
||||
{
|
||||
void f_l2normhelper(int *, double *, double *, double *,
|
||||
double &, double &, double &,
|
||||
double &, double &, double &,
|
||||
double *, double &, int &);
|
||||
}
|
||||
|
||||
extern "C"
|
||||
{
|
||||
void f_l2normhelper_sh(int *, double *, double *, double *,
|
||||
double &, double &, double &,
|
||||
double &, double &, double &,
|
||||
double *, double &, int &, int &, int &);
|
||||
}
|
||||
extern "C"
|
||||
{
|
||||
void f_l2normhelper(int *, double *, double *, double *,
|
||||
double &, double &, double &,
|
||||
double &, double &, double &,
|
||||
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 *,
|
||||
double &, double &, double &,
|
||||
double &, double &, double &,
|
||||
double *, double &, int &, int &, int &);
|
||||
}
|
||||
|
||||
extern "C"
|
||||
{
|
||||
|
||||
@@ -16,66 +16,115 @@ using namespace std;
|
||||
#include <string.h>
|
||||
#include <math.h>
|
||||
#endif
|
||||
|
||||
// Intel oneMKL LAPACK interface
|
||||
#include <mkl_lapacke.h>
|
||||
/* Linear equation solution using Intel oneMKL LAPACK.
|
||||
/* Linear equation solution by Gauss-Jordan elimination.
|
||||
a[0..n-1][0..n-1] is the input matrix. b[0..n-1] is input
|
||||
containing the right-hand side vectors. On output a is
|
||||
replaced by its matrix inverse, and b is replaced by the
|
||||
corresponding set of solution vectors.
|
||||
|
||||
Mathematical equivalence:
|
||||
Solves: A * x = b => x = A^(-1) * b
|
||||
Original Gauss-Jordan and LAPACK dgesv/dgetri produce identical results
|
||||
within numerical precision. */
|
||||
corresponding set of solution vectors */
|
||||
|
||||
int gaussj(double *a, double *b, int n)
|
||||
{
|
||||
// Allocate pivot array and workspace
|
||||
lapack_int *ipiv = new lapack_int[n];
|
||||
lapack_int info;
|
||||
double swap;
|
||||
|
||||
// Make a copy of matrix a for solving (dgesv modifies it to LU form)
|
||||
double *a_copy = new double[n * n];
|
||||
for (int i = 0; i < n * n; i++) {
|
||||
a_copy[i] = a[i];
|
||||
int *indxc, *indxr, *ipiv;
|
||||
indxc = new int[n];
|
||||
indxr = new int[n];
|
||||
ipiv = new int[n];
|
||||
|
||||
int i, icol, irow, j, k, l, ll;
|
||||
double big, dum, pivinv, temp;
|
||||
|
||||
for (j = 0; j < n; j++)
|
||||
ipiv[j] = 0;
|
||||
for (i = 0; i < n; i++)
|
||||
{
|
||||
big = 0.0;
|
||||
for (j = 0; j < n; j++)
|
||||
if (ipiv[j] != 1)
|
||||
for (k = 0; k < n; k++)
|
||||
{
|
||||
if (ipiv[k] == 0)
|
||||
{
|
||||
if (fabs(a[j * n + k]) >= big)
|
||||
{
|
||||
big = fabs(a[j * n + k]);
|
||||
irow = j;
|
||||
icol = k;
|
||||
}
|
||||
}
|
||||
else if (ipiv[k] > 1)
|
||||
{
|
||||
cout << "gaussj: Singular Matrix-1" << endl;
|
||||
for (int ii = 0; ii < n; ii++)
|
||||
{
|
||||
for (int jj = 0; jj < n; jj++)
|
||||
cout << a[ii * n + jj] << " ";
|
||||
cout << endl;
|
||||
}
|
||||
return 1; // error return
|
||||
}
|
||||
}
|
||||
|
||||
ipiv[icol] = ipiv[icol] + 1;
|
||||
if (irow != icol)
|
||||
{
|
||||
for (l = 0; l < n; l++)
|
||||
{
|
||||
swap = a[irow * n + l];
|
||||
a[irow * n + l] = a[icol * n + l];
|
||||
a[icol * n + l] = swap;
|
||||
}
|
||||
|
||||
swap = b[irow];
|
||||
b[irow] = b[icol];
|
||||
b[icol] = swap;
|
||||
}
|
||||
|
||||
indxr[i] = irow;
|
||||
indxc[i] = icol;
|
||||
|
||||
if (a[icol * n + icol] == 0.0)
|
||||
{
|
||||
cout << "gaussj: Singular Matrix-2" << endl;
|
||||
for (int ii = 0; ii < n; ii++)
|
||||
{
|
||||
for (int jj = 0; jj < n; jj++)
|
||||
cout << a[ii * n + jj] << " ";
|
||||
cout << endl;
|
||||
}
|
||||
return 1; // error return
|
||||
}
|
||||
|
||||
pivinv = 1.0 / a[icol * n + icol];
|
||||
a[icol * n + icol] = 1.0;
|
||||
for (l = 0; l < n; l++)
|
||||
a[icol * n + l] *= pivinv;
|
||||
b[icol] *= pivinv;
|
||||
for (ll = 0; ll < n; ll++)
|
||||
if (ll != icol)
|
||||
{
|
||||
dum = a[ll * n + icol];
|
||||
a[ll * n + icol] = 0.0;
|
||||
for (l = 0; l < n; l++)
|
||||
a[ll * n + l] -= a[icol * n + l] * dum;
|
||||
b[ll] -= b[icol] * dum;
|
||||
}
|
||||
}
|
||||
|
||||
// Step 1: Solve linear system A*x = b using LU decomposition
|
||||
// LAPACKE_dgesv uses column-major by default, but we use row-major
|
||||
info = LAPACKE_dgesv(LAPACK_ROW_MAJOR, n, 1, a_copy, n, ipiv, b, 1);
|
||||
|
||||
if (info != 0) {
|
||||
cout << "gaussj: Singular Matrix (dgesv info=" << info << ")" << endl;
|
||||
delete[] ipiv;
|
||||
delete[] a_copy;
|
||||
return 1;
|
||||
}
|
||||
|
||||
// Step 2: Compute matrix inverse A^(-1) using LU factorization
|
||||
// First do LU factorization of original matrix a
|
||||
info = LAPACKE_dgetrf(LAPACK_ROW_MAJOR, n, n, a, n, ipiv);
|
||||
|
||||
if (info != 0) {
|
||||
cout << "gaussj: Singular Matrix (dgetrf info=" << info << ")" << endl;
|
||||
delete[] ipiv;
|
||||
delete[] a_copy;
|
||||
return 1;
|
||||
}
|
||||
|
||||
// Then compute inverse from LU factorization
|
||||
info = LAPACKE_dgetri(LAPACK_ROW_MAJOR, n, a, n, ipiv);
|
||||
|
||||
if (info != 0) {
|
||||
cout << "gaussj: Singular Matrix (dgetri info=" << info << ")" << endl;
|
||||
delete[] ipiv;
|
||||
delete[] a_copy;
|
||||
return 1;
|
||||
for (l = n - 1; l >= 0; l--)
|
||||
{
|
||||
if (indxr[l] != indxc[l])
|
||||
for (k = 0; k < n; k++)
|
||||
{
|
||||
swap = a[k * n + indxr[l]];
|
||||
a[k * n + indxr[l]] = a[k * n + indxc[l]];
|
||||
a[k * n + indxc[l]] = swap;
|
||||
}
|
||||
}
|
||||
|
||||
delete[] indxc;
|
||||
delete[] indxr;
|
||||
delete[] ipiv;
|
||||
delete[] a_copy;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
@@ -512,10 +512,11 @@
|
||||
IMPLICIT DOUBLE PRECISION (A-H,O-Z)
|
||||
DIMENSION V(N),W(N)
|
||||
! SUBROUTINE TO COMPUTE DOUBLE PRECISION VECTOR DOT PRODUCT.
|
||||
! Optimized using Intel oneMKL BLAS ddot
|
||||
! Mathematical equivalence: DGVV = sum_{i=1}^{N} V(i)*W(i)
|
||||
|
||||
DOUBLE PRECISION, EXTERNAL :: DDOT
|
||||
DGVV = DDOT(N, V, 1, W, 1)
|
||||
SUM = 0.0D0
|
||||
DO 10 I = 1,N
|
||||
SUM = SUM + V(I)*W(I)
|
||||
10 CONTINUE
|
||||
DGVV = SUM
|
||||
RETURN
|
||||
END
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
#ifndef MICRODEF_H
|
||||
#define MICRODEF_H
|
||||
|
||||
#include "macrodef.fh"
|
||||
#include "macrodef.fh"
|
||||
|
||||
// application parameters
|
||||
|
||||
|
||||
@@ -1,11 +1,25 @@
|
||||
|
||||
|
||||
include makefile.inc
|
||||
|
||||
.SUFFIXES: .o .f90 .C .for .cu
|
||||
|
||||
.f90.o:
|
||||
$(f90) $(f90appflags) -c $< -o $@
|
||||
|
||||
|
||||
include makefile.inc
|
||||
|
||||
## polint(ordn=6) kernel selector:
|
||||
## 1 (default): barycentric fast path
|
||||
## 0 : fallback to Neville path
|
||||
POLINT6_USE_BARY ?= 1
|
||||
POLINT6_FLAG = -DPOLINT6_USE_BARYCENTRIC=$(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:
|
||||
$(f90) $(f90appflags) -c $< -o $@
|
||||
|
||||
.C.o:
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
@@ -13,8 +27,14 @@ include makefile.inc
|
||||
.for.o:
|
||||
$(f77) -c $< -o $@
|
||||
|
||||
.cu.o:
|
||||
$(Cu) $(CUDA_APP_FLAGS) -c $< -o $@ $(CUDA_LIB_PATH)
|
||||
.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\
|
||||
@@ -95,8 +115,8 @@ ABE: $(C++FILES) $(F90FILES) $(F77FILES) $(AHFDOBJS)
|
||||
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)
|
||||
TwoPunctureABE: $(TwoPunctureFILES)
|
||||
$(CLINKER) $(TP_OPTFLAGS) -qopenmp -o $@ $(TwoPunctureFILES) $(LDLIBS)
|
||||
|
||||
clean:
|
||||
rm *.o ABE ABEGPU TwoPunctureABE make.log -f
|
||||
|
||||
@@ -1,30 +1,32 @@
|
||||
|
||||
## GCC version (commented out)
|
||||
## filein = -I/usr/include -I/usr/lib/x86_64-linux-gnu/mpich/include -I/usr/lib/x86_64-linux-gnu/openmpi/lib/ -I/usr/lib/gcc/x86_64-linux-gnu/11/ -I/usr/include/c++/11/
|
||||
## filein = -I/usr/include/ -I/usr/include/openmpi-x86_64/ -I/usr/lib/x86_64-linux-gnu/openmpi/include/ -I/usr/lib/x86_64-linux-gnu/openmpi/lib/ -I/usr/lib/gcc/x86_64-linux-gnu/11/ -I/usr/include/c++/11/
|
||||
## LDLIBS = -L/usr/lib/x86_64-linux-gnu -L/usr/lib64 -L/usr/lib/gcc/x86_64-linux-gnu/11 -lgfortran -lmpi -lgfortran
|
||||
|
||||
## Intel oneAPI version with oneMKL (Optimized for performance)
|
||||
## Intel oneAPI version with oneMKL
|
||||
filein = -I/usr/include/ -I${MKLROOT}/include
|
||||
|
||||
## Using sequential MKL (OpenMP disabled for better single-threaded performance)
|
||||
## Added -lifcore for Intel Fortran runtime and -limf for Intel math library
|
||||
LDLIBS = -L${MKLROOT}/lib -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lifcore -limf -lpthread -lm -ldl
|
||||
## Use sequential oneMKL to avoid introducing extra OpenMP behavior into ABE.
|
||||
LDLIBS = -L${MKLROOT}/lib -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lifcore -limf -lpthread -lm -ldl -liomp5
|
||||
|
||||
## Optional Intel oneTBB allocator, kept aligned with main's build environment.
|
||||
USE_TBBMALLOC ?= 1
|
||||
TBBMALLOC_SO ?= /home/intel/oneapi/2025.3/lib/libtbbmalloc.so
|
||||
ifneq ($(wildcard $(TBBMALLOC_SO)),)
|
||||
TBBMALLOC_LIBS = -Wl,--no-as-needed $(TBBMALLOC_SO) -Wl,--as-needed
|
||||
else
|
||||
TBBMALLOC_LIBS = -Wl,--no-as-needed -ltbbmalloc -Wl,--as-needed
|
||||
endif
|
||||
ifeq ($(USE_TBBMALLOC),1)
|
||||
LDLIBS := $(TBBMALLOC_LIBS) $(LDLIBS)
|
||||
endif
|
||||
|
||||
## Aggressive optimization flags:
|
||||
## -O3: Maximum optimization
|
||||
## -xHost: Optimize for the host CPU architecture (Intel/AMD compatible)
|
||||
## -fp-model fast=2: Aggressive floating-point optimizations
|
||||
## -fma: Enable fused multiply-add instructions
|
||||
## Note: OpenMP has been disabled (-qopenmp removed) due to performance issues
|
||||
CXXAPPFLAGS = -O3 -xHost -fp-model fast=2 -fma \
|
||||
-Dfortran3 -Dnewc -I${MKLROOT}/include
|
||||
f90appflags = -O3 -xHost -fp-model fast=2 -fma \
|
||||
-fpp -I${MKLROOT}/include
|
||||
f90 = ifx
|
||||
f77 = ifx
|
||||
CXX = icpx
|
||||
CC = icx
|
||||
CLINKER = mpiicpx
|
||||
CLINKER = mpiicpx
|
||||
|
||||
Cu = nvcc
|
||||
CUDA_LIB_PATH = -L/usr/lib/cuda/lib64 -I/usr/include -I/usr/lib/cuda/include
|
||||
|
||||
@@ -253,19 +253,7 @@ def generate_macrodef_h():
|
||||
# Define macro buffer_width
|
||||
# number of buffer points for mesh-refinement interfaces
|
||||
|
||||
# Calculate ghost_width based on Finite_Diffenence_Method to optimize buffer_width
|
||||
if ( input_data.Finite_Diffenence_Method == "2nd-order" ):
|
||||
gw = 2
|
||||
elif ( input_data.Finite_Diffenence_Method == "4th-order" ):
|
||||
gw = 3
|
||||
elif ( input_data.Finite_Diffenence_Method == "6th-order" ):
|
||||
gw = 4
|
||||
elif ( input_data.Finite_Diffenence_Method == "8th-order" ):
|
||||
gw = 5
|
||||
else:
|
||||
gw = 5 # Default conservative value
|
||||
|
||||
print( f"#define buffer_width {gw + 1}", file=file1 )
|
||||
print( "#define buffer_width 6", file=file1 )
|
||||
print( file=file1 )
|
||||
|
||||
# Define macro SC_width as buffer_width
|
||||
@@ -404,17 +392,6 @@ def generate_macrodef_fh():
|
||||
print( "# Finite_Difference_Method #define ghost_width setting error!!!", file=file1 )
|
||||
print( file=file1 )
|
||||
|
||||
# Define macro DEBUG_NAN_CHECK
|
||||
# 0: off (default), 1: on
|
||||
|
||||
debug_nan_check = getattr(input_data, "Debug_NaN_Check", 0)
|
||||
if debug_nan_check:
|
||||
print( "#define DEBUG_NAN_CHECK 1", file=file1 )
|
||||
print( file=file1 )
|
||||
else:
|
||||
print( "#define DEBUG_NAN_CHECK 0", file=file1 )
|
||||
print( file=file1 )
|
||||
|
||||
# Whether to use a shell-patch grid
|
||||
# use shell or not
|
||||
|
||||
@@ -537,9 +514,6 @@ def generate_macrodef_fh():
|
||||
print( " 6th order: 4", file=file1 )
|
||||
print( " 8th order: 5", file=file1 )
|
||||
print( file=file1 )
|
||||
print( "define DEBUG_NAN_CHECK", file=file1 )
|
||||
print( " 0: off (default), 1: on", file=file1 )
|
||||
print( file=file1 )
|
||||
print( "define WithShell", file=file1 )
|
||||
print( " use shell or not", file=file1 )
|
||||
print( file=file1 )
|
||||
|
||||
@@ -35,8 +35,7 @@ Equation_Class = "BSSN" ## Evolution Equation: choose
|
||||
## If "BSSN-EScalar" is chosen, it is necessary to set other parameters below
|
||||
Initial_Data_Method = "Ansorg-TwoPuncture" ## initial data method: choose "Ansorg-TwoPuncture", "Lousto-Analytical", "Cao-Analytical", "KerrSchild-Analytical"
|
||||
Time_Evolution_Method = "runge-kutta-45" ## time evolution method: choose "runge-kutta-45"
|
||||
Finite_Diffenence_Method = "4th-order" ## finite-difference method: choose "2nd-order", "4th-order", "6th-order", "8th-order"
|
||||
Debug_NaN_Check = 0 ## enable NaN checks in compute_rhs_bssn: 0 (off) or 1 (on)
|
||||
Finite_Diffenence_Method = "4th-order" ## finite-difference method: choose "2nd-order", "4th-order", "6th-order", "8th-order"
|
||||
|
||||
#################################################
|
||||
|
||||
|
||||
@@ -11,18 +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"
|
||||
NUMACTL_CPU_BIND = ""
|
||||
|
||||
## Build parallelism configuration
|
||||
## Use nohz_full cores (4-55, 60-111) for compilation: 52 + 52 = 104 cores
|
||||
## Set make -j to utilize available cores for faster builds
|
||||
BUILD_JOBS = 14
|
||||
|
||||
|
||||
##################################################################
|
||||
|
||||
@@ -38,11 +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( )
|
||||
@@ -79,8 +67,8 @@ def makefile_TwoPunctureABE():
|
||||
print( " Compiling the AMSS-NCKU executable file TwoPunctureABE " )
|
||||
print( )
|
||||
|
||||
## Build command with CPU binding to nohz_full cores
|
||||
makefile_command = f"{NUMACTL_CPU_BIND} make -j{BUILD_JOBS} TwoPunctureABE"
|
||||
## Build command
|
||||
makefile_command = "make" + " TwoPunctureABE"
|
||||
|
||||
## Execute the command with subprocess.Popen and stream output
|
||||
makefile_process = subprocess.Popen(makefile_command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True)
|
||||
@@ -117,10 +105,10 @@ def run_ABE():
|
||||
## Define the command to run; cast other values to strings as needed
|
||||
|
||||
if (input_data.GPU_Calculation == "no"):
|
||||
mpi_command = NUMACTL_CPU_BIND + " mpirun -np " + str(input_data.MPI_processes) + " ./ABE"
|
||||
mpi_command = "mpirun -np " + str(input_data.MPI_processes) + " ./ABE"
|
||||
mpi_command_outfile = "ABE_out.log"
|
||||
elif (input_data.GPU_Calculation == "yes"):
|
||||
mpi_command = NUMACTL_CPU_BIND + " mpirun -np " + str(input_data.MPI_processes) + " ./ABEGPU"
|
||||
mpi_command = "mpirun -np " + str(input_data.MPI_processes) + " ./ABEGPU"
|
||||
mpi_command_outfile = "ABEGPU_out.log"
|
||||
|
||||
## Execute the MPI command and stream output
|
||||
@@ -159,7 +147,7 @@ def run_TwoPunctureABE():
|
||||
print( )
|
||||
|
||||
## Define the command to run
|
||||
TwoPuncture_command = NUMACTL_CPU_BIND + " ./TwoPunctureABE"
|
||||
TwoPuncture_command = "./TwoPunctureABE"
|
||||
TwoPuncture_command_outfile = "TwoPunctureABE_out.log"
|
||||
|
||||
## Execute the command with subprocess.Popen and stream output
|
||||
|
||||
12
parallel_plot_helper.py
Normal file
12
parallel_plot_helper.py
Normal file
@@ -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)
|
||||
@@ -8,11 +8,13 @@
|
||||
##
|
||||
#################################################
|
||||
|
||||
import numpy ## numpy for array operations
|
||||
import scipy ## scipy for interpolation and signal processing
|
||||
import math
|
||||
import matplotlib.pyplot as plt ## matplotlib for plotting
|
||||
import os ## os for system/file operations
|
||||
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
|
||||
|
||||
import AMSS_NCKU_Input as input_data
|
||||
|
||||
|
||||
@@ -6,17 +6,22 @@
|
||||
## Author: Xiaoqu
|
||||
## Dates: 2024/10/01 --- 2025/09/14
|
||||
##
|
||||
#################################################
|
||||
|
||||
import numpy
|
||||
import scipy
|
||||
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
|
||||
#################################################
|
||||
|
||||
## 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
|
||||
|
||||
|
||||
#########################################################################################
|
||||
@@ -92,9 +97,9 @@ def plot_binary_data( filename, binary_outdir, figure_outdir ):
|
||||
|
||||
|
||||
|
||||
####################################################################################
|
||||
|
||||
# Plot a single binary dataset (2D slices and 3D surface)
|
||||
####################################################################################
|
||||
|
||||
# Plot a single binary dataset (2D slices and 3D surface)
|
||||
|
||||
def get_data_xy( Rmin, Rmax, n, data0, time, figure_title, figure_outdir ):
|
||||
|
||||
@@ -188,7 +193,15 @@ def get_data_xy( Rmin, Rmax, n, data0, time, figure_title, figure_outdir ):
|
||||
plt.savefig( os.path.join(figure_surfaceplot_outdir, figure_title + " time = " + str(time) + " surface_plot.pdf") ) # save figure
|
||||
plt.close()
|
||||
|
||||
return
|
||||
|
||||
####################################################################################
|
||||
return
|
||||
|
||||
####################################################################################
|
||||
|
||||
## 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])
|
||||
|
||||
|
||||
@@ -6,15 +6,20 @@
|
||||
## 2024/10/01 --- 2025/09/14
|
||||
##
|
||||
#################################################
|
||||
|
||||
import numpy ## numpy for array operations
|
||||
import matplotlib.pyplot as plt ## matplotlib for plotting
|
||||
from mpl_toolkits.mplot3d import Axes3D ## needed for 3D plots
|
||||
import glob
|
||||
import os ## operating system utilities
|
||||
|
||||
import plot_binary_data
|
||||
import AMSS_NCKU_Input as input_data
|
||||
|
||||
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
|
||||
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
|
||||
|
||||
@@ -50,13 +55,37 @@ def generate_binary_data_plot( binary_outdir, figure_outdir ):
|
||||
file_list.append(x)
|
||||
print(x)
|
||||
|
||||
## Plot each file in the list
|
||||
for filename in file_list:
|
||||
print(filename)
|
||||
plot_binary_data.plot_binary_data(filename, binary_outdir, figure_outdir)
|
||||
|
||||
print( )
|
||||
print( " Binary Data Plot Has been Finished " )
|
||||
## 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)
|
||||
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 " )
|
||||
print( )
|
||||
|
||||
return
|
||||
|
||||
Reference in New Issue
Block a user