Compare commits
3 Commits
main-upstr
...
cjy-oneapi
| Author | SHA1 | Date | |
|---|---|---|---|
|
3914659ebb | ||
|
|
039dce4d65 | ||
|
|
c524228d23 |
6
.idea/vcs.xml
generated
6
.idea/vcs.xml
generated
@@ -1,6 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project version="4">
|
||||
<component name="VcsDirectoryMappings">
|
||||
<mapping directory="" vcs="Git" />
|
||||
</component>
|
||||
</project>
|
||||
@@ -16,7 +16,7 @@ import numpy
|
||||
File_directory = "GW150914" ## output file directory
|
||||
Output_directory = "binary_output" ## binary data file directory
|
||||
## The file directory name should not be too long
|
||||
MPI_processes = 64 ## number of mpi processes used in the simulation
|
||||
MPI_processes = 48 ## 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)
|
||||
|
||||
@@ -8,14 +8,6 @@
|
||||
##
|
||||
##################################################################
|
||||
|
||||
## Guard against re-execution by multiprocessing child processes.
|
||||
## Without this, using 'spawn' or 'forkserver' context would cause every
|
||||
## worker to re-run the entire script, spawning exponentially more
|
||||
## workers (fork bomb).
|
||||
if __name__ != '__main__':
|
||||
import sys as _sys
|
||||
_sys.exit(0)
|
||||
|
||||
|
||||
##################################################################
|
||||
|
||||
@@ -126,6 +118,11 @@ setup.generate_AMSSNCKU_input()
|
||||
#inputvalue = input() ## Wait for user input (press Enter) to proceed
|
||||
#print()
|
||||
|
||||
setup.print_puncture_information()
|
||||
|
||||
|
||||
##################################################################
|
||||
|
||||
## Generate AMSS-NCKU program input files based on the configured parameters
|
||||
|
||||
print( )
|
||||
@@ -265,12 +262,6 @@ if not os.path.exists( ABE_file ):
|
||||
## Copy the executable ABE (or ABEGPU) into the run directory
|
||||
shutil.copy2(ABE_file, output_directory)
|
||||
|
||||
## Copy interp load balance profile if present (for optimize pass)
|
||||
interp_lb_profile = os.path.join(AMSS_NCKU_source_copy, "interp_lb_profile.bin")
|
||||
if os.path.exists(interp_lb_profile):
|
||||
shutil.copy2(interp_lb_profile, output_directory)
|
||||
print( " Copied interp_lb_profile.bin to run directory " )
|
||||
|
||||
###########################
|
||||
|
||||
## If the initial-data method is TwoPuncture, copy the TwoPunctureABE executable to the run directory
|
||||
@@ -307,7 +298,7 @@ if (input_data.Initial_Data_Method == "Ansorg-TwoPuncture" ):
|
||||
|
||||
import generate_TwoPuncture_input
|
||||
|
||||
generate_TwoPuncture_input.generate_AMSSNCKU_TwoPuncture_input(numerical_grid.puncture_data)
|
||||
generate_TwoPuncture_input.generate_AMSSNCKU_TwoPuncture_input()
|
||||
|
||||
print( )
|
||||
print( " The input parfile for the TwoPunctureABE executable has been generated. " )
|
||||
@@ -349,7 +340,7 @@ if (input_data.Initial_Data_Method == "Ansorg-TwoPuncture" ):
|
||||
|
||||
import renew_puncture_parameter
|
||||
|
||||
renew_puncture_parameter.append_AMSSNCKU_BSSN_input(File_directory, output_directory, numerical_grid.puncture_data)
|
||||
renew_puncture_parameter.append_AMSSNCKU_BSSN_input(File_directory, output_directory)
|
||||
|
||||
|
||||
## Generated AMSS-NCKU input filename
|
||||
@@ -433,31 +424,26 @@ print(
|
||||
|
||||
import plot_xiaoqu
|
||||
import plot_GW_strain_amplitude_xiaoqu
|
||||
from parallel_plot_helper import run_plot_tasks_parallel
|
||||
|
||||
plot_tasks = []
|
||||
|
||||
## Plot black hole trajectory
|
||||
plot_tasks.append( ( plot_xiaoqu.generate_puncture_orbit_plot, (binary_results_directory, figure_directory) ) )
|
||||
plot_tasks.append( ( plot_xiaoqu.generate_puncture_orbit_plot3D, (binary_results_directory, figure_directory) ) )
|
||||
plot_xiaoqu.generate_puncture_orbit_plot( binary_results_directory, figure_directory )
|
||||
plot_xiaoqu.generate_puncture_orbit_plot3D( binary_results_directory, figure_directory )
|
||||
|
||||
## Plot black hole separation vs. time
|
||||
plot_tasks.append( ( plot_xiaoqu.generate_puncture_distence_plot, (binary_results_directory, figure_directory) ) )
|
||||
plot_xiaoqu.generate_puncture_distence_plot( binary_results_directory, figure_directory )
|
||||
|
||||
## Plot gravitational waveforms (psi4 and strain amplitude)
|
||||
for i in range(input_data.Detector_Number):
|
||||
plot_tasks.append( ( plot_xiaoqu.generate_gravitational_wave_psi4_plot, (binary_results_directory, figure_directory, i) ) )
|
||||
plot_tasks.append( ( plot_GW_strain_amplitude_xiaoqu.generate_gravitational_wave_amplitude_plot, (binary_results_directory, figure_directory, i) ) )
|
||||
plot_xiaoqu.generate_gravitational_wave_psi4_plot( binary_results_directory, figure_directory, i )
|
||||
plot_GW_strain_amplitude_xiaoqu.generate_gravitational_wave_amplitude_plot( binary_results_directory, figure_directory, i )
|
||||
|
||||
## Plot ADM mass evolution
|
||||
for i in range(input_data.Detector_Number):
|
||||
plot_tasks.append( ( plot_xiaoqu.generate_ADMmass_plot, (binary_results_directory, figure_directory, i) ) )
|
||||
plot_xiaoqu.generate_ADMmass_plot( binary_results_directory, figure_directory, i )
|
||||
|
||||
## Plot Hamiltonian constraint violation over time
|
||||
for i in range(input_data.grid_level):
|
||||
plot_tasks.append( ( plot_xiaoqu.generate_constraint_check_plot, (binary_results_directory, figure_directory, i) ) )
|
||||
|
||||
run_plot_tasks_parallel(plot_tasks)
|
||||
plot_xiaoqu.generate_constraint_check_plot( binary_results_directory, figure_directory, i )
|
||||
|
||||
## Plot stored binary data
|
||||
plot_xiaoqu.generate_binary_data_plot( binary_results_directory, figure_directory )
|
||||
|
||||
@@ -1,19 +1,10 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
AMSS-NCKU GW150914 Simulation Regression Test Script (Comprehensive Version)
|
||||
AMSS-NCKU GW150914 Simulation Regression Test Script
|
||||
|
||||
Verification Requirements:
|
||||
1. RMS errors < 1% for:
|
||||
- 3D Vector Total RMS
|
||||
- X Component RMS
|
||||
- Y Component RMS
|
||||
- Z Component RMS
|
||||
1. XY-plane trajectory RMS error < 1% (Optimized vs. baseline, max of BH1 and BH2)
|
||||
2. ADM constraint violation < 2 (Grid Level 0)
|
||||
3. The following figure PDFs must match GW150914-origin exactly after rasterization:
|
||||
- ADM_Constraint_Grid_Level_0.pdf
|
||||
- BH_Trajectory_21_XY.pdf
|
||||
- BH_Trajectory_XY.pdf
|
||||
The script also reports the percentage of differing pixels for each figure.
|
||||
|
||||
RMS Calculation Method:
|
||||
- Computes trajectory deviation on the XY plane independently for BH1 and BH2
|
||||
@@ -28,10 +19,6 @@ Reference: GW150914-origin (baseline simulation)
|
||||
import numpy as np
|
||||
import sys
|
||||
import os
|
||||
import shutil
|
||||
import subprocess
|
||||
import tempfile
|
||||
from PIL import Image
|
||||
|
||||
# ANSI Color Codes
|
||||
class Color:
|
||||
@@ -71,187 +58,78 @@ def load_constraint_data(filepath):
|
||||
return np.array(data)
|
||||
|
||||
|
||||
def resolve_figure_dir(path):
|
||||
"""Resolve the sibling figure directory from an output or figure path."""
|
||||
normalized = os.path.normpath(path)
|
||||
if os.path.basename(normalized) == "figure":
|
||||
return normalized
|
||||
return os.path.join(os.path.dirname(normalized), "figure")
|
||||
|
||||
|
||||
def render_pdf_to_images(pdf_path, dpi=150):
|
||||
"""Render a PDF to RGB images using Ghostscript."""
|
||||
gs_path = shutil.which("gs")
|
||||
if gs_path is None:
|
||||
raise RuntimeError("Ghostscript executable 'gs' was not found in PATH")
|
||||
|
||||
with tempfile.TemporaryDirectory(prefix="amss_verify_pdf_") as temp_dir:
|
||||
output_pattern = os.path.join(temp_dir, "page-%03d.ppm")
|
||||
cmd = [
|
||||
gs_path,
|
||||
"-q",
|
||||
"-dSAFER",
|
||||
"-dBATCH",
|
||||
"-dNOPAUSE",
|
||||
"-sDEVICE=ppmraw",
|
||||
f"-r{dpi}",
|
||||
f"-o{output_pattern}",
|
||||
pdf_path
|
||||
]
|
||||
|
||||
try:
|
||||
subprocess.run(cmd, check=True, stdout=subprocess.DEVNULL, stderr=subprocess.PIPE, text=True)
|
||||
except subprocess.CalledProcessError as exc:
|
||||
message = exc.stderr.strip() or str(exc)
|
||||
raise RuntimeError(f"Failed to render PDF '{pdf_path}': {message}") from exc
|
||||
|
||||
ppm_files = sorted(
|
||||
os.path.join(temp_dir, filename)
|
||||
for filename in os.listdir(temp_dir)
|
||||
if filename.endswith(".ppm")
|
||||
)
|
||||
|
||||
if not ppm_files:
|
||||
raise RuntimeError(f"No rendered pages were produced for '{pdf_path}'")
|
||||
|
||||
images = []
|
||||
for ppm_file in ppm_files:
|
||||
with Image.open(ppm_file) as img:
|
||||
images.append(np.array(img.convert("RGB"), dtype=np.uint8))
|
||||
|
||||
return images
|
||||
|
||||
|
||||
def compare_rendered_pages(ref_img, target_img):
|
||||
"""Return (different_pixels, total_pixels) for two rendered RGB pages."""
|
||||
ref_h, ref_w = ref_img.shape[:2]
|
||||
tgt_h, tgt_w = target_img.shape[:2]
|
||||
total_pixels = max(ref_h, tgt_h) * max(ref_w, tgt_w)
|
||||
|
||||
if ref_h == tgt_h and ref_w == tgt_w:
|
||||
different_pixels = int(np.count_nonzero(np.any(ref_img != target_img, axis=2)))
|
||||
return different_pixels, total_pixels
|
||||
|
||||
diff_mask = np.ones((max(ref_h, tgt_h), max(ref_w, tgt_w)), dtype=bool)
|
||||
overlap_h = min(ref_h, tgt_h)
|
||||
overlap_w = min(ref_w, tgt_w)
|
||||
overlap_diff = np.any(ref_img[:overlap_h, :overlap_w] != target_img[:overlap_h, :overlap_w], axis=2)
|
||||
diff_mask[:overlap_h, :overlap_w] = overlap_diff
|
||||
different_pixels = int(np.count_nonzero(diff_mask))
|
||||
return different_pixels, total_pixels
|
||||
|
||||
|
||||
def compare_pdf_images(ref_pdf, target_pdf, dpi=150, threshold_percent=0.001):
|
||||
"""Compare two PDFs by rasterizing them and counting differing pixels."""
|
||||
ref_pages = render_pdf_to_images(ref_pdf, dpi=dpi)
|
||||
target_pages = render_pdf_to_images(target_pdf, dpi=dpi)
|
||||
|
||||
total_pixels = 0
|
||||
different_pixels = 0
|
||||
max_pages = max(len(ref_pages), len(target_pages))
|
||||
|
||||
for page_idx in range(max_pages):
|
||||
if page_idx < len(ref_pages) and page_idx < len(target_pages):
|
||||
page_diff, page_total = compare_rendered_pages(ref_pages[page_idx], target_pages[page_idx])
|
||||
else:
|
||||
existing_page = ref_pages[page_idx] if page_idx < len(ref_pages) else target_pages[page_idx]
|
||||
page_total = existing_page.shape[0] * existing_page.shape[1]
|
||||
page_diff = page_total
|
||||
|
||||
total_pixels += page_total
|
||||
different_pixels += page_diff
|
||||
|
||||
diff_percent = (different_pixels / total_pixels * 100.0) if total_pixels else 0.0
|
||||
return {
|
||||
"different_pixels": different_pixels,
|
||||
"total_pixels": total_pixels,
|
||||
"diff_percent": diff_percent,
|
||||
"pages_ref": len(ref_pages),
|
||||
"pages_target": len(target_pages),
|
||||
"passed": diff_percent < threshold_percent
|
||||
}
|
||||
|
||||
|
||||
def compare_required_figures(reference_figure_dir, target_figure_dir):
|
||||
"""Compare the required GW150914 figure PDFs."""
|
||||
figure_names = [
|
||||
"ADM_Constraint_Grid_Level_0.pdf",
|
||||
"BH_Trajectory_21_XY.pdf",
|
||||
"BH_Trajectory_XY.pdf"
|
||||
]
|
||||
|
||||
results = []
|
||||
for figure_name in figure_names:
|
||||
ref_pdf = os.path.join(reference_figure_dir, figure_name)
|
||||
target_pdf = os.path.join(target_figure_dir, figure_name)
|
||||
|
||||
if not os.path.exists(ref_pdf):
|
||||
raise FileNotFoundError(f"Reference figure not found: {ref_pdf}")
|
||||
if not os.path.exists(target_pdf):
|
||||
raise FileNotFoundError(f"Target figure not found: {target_pdf}")
|
||||
|
||||
comparison = compare_pdf_images(ref_pdf, target_pdf)
|
||||
comparison["name"] = figure_name
|
||||
results.append(comparison)
|
||||
|
||||
return results
|
||||
|
||||
def calculate_all_rms_errors(bh_data_ref, bh_data_target):
|
||||
def calculate_rms_error(bh_data_ref, bh_data_target):
|
||||
"""
|
||||
Calculate 3D Vector RMS and component-wise RMS (X, Y, Z) independently.
|
||||
Uses r = sqrt(x^2 + y^2) as the denominator for all error normalizations.
|
||||
Returns the maximum error between BH1 and BH2 for each category.
|
||||
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"
|
||||
|
||||
results = {}
|
||||
# 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]
|
||||
|
||||
for bh in ['1', '2']:
|
||||
x_r, y_r, z_r = bh_data_ref[f'x{bh}'][:M], bh_data_ref[f'y{bh}'][:M], bh_data_ref[f'z{bh}'][:M]
|
||||
x_n, y_n, z_n = bh_data_target[f'x{bh}'][:M], bh_data_target[f'y{bh}'][:M], bh_data_target[f'z{bh}'][:M]
|
||||
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]
|
||||
|
||||
# 核心修改：根据组委会的邮件指示，分母统一使用 r = sqrt(x^2 + y^2)
|
||||
r_ref = np.sqrt(x_r**2 + y_r**2)
|
||||
r_new = np.sqrt(x_n**2 + y_n**2)
|
||||
denom_max = np.maximum(r_ref, r_new)
|
||||
# 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)
|
||||
|
||||
valid = denom_max > 1e-15
|
||||
if np.sum(valid) < 10:
|
||||
results[f'BH{bh}'] = { '3D_Vector': 0.0, 'X_Component': 0.0, 'Y_Component': 0.0, 'Z_Component': 0.0 }
|
||||
continue
|
||||
# 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)
|
||||
|
||||
def calc_rms(delta):
|
||||
# 将对应分量的偏差除以统一的轨道半径分母 denom_max
|
||||
return np.sqrt(np.mean((delta[valid] / denom_max[valid])**2)) * 100
|
||||
# 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"
|
||||
|
||||
# 1. Total 3D Vector RMS
|
||||
delta_vec = np.sqrt((x_r - x_n)**2 + (y_r - y_n)**2 + (z_r - z_n)**2)
|
||||
rms_3d = calc_rms(delta_vec)
|
||||
terms1 = (delta_r1[valid_mask1] / r1_max[valid_mask1])**2
|
||||
rms_bh1 = np.sqrt(np.mean(terms1)) * 100
|
||||
|
||||
# 2. Component-wise RMS (分离计算各轴，但共用半径分母)
|
||||
rms_x = calc_rms(np.abs(x_r - x_n))
|
||||
rms_y = calc_rms(np.abs(y_r - y_n))
|
||||
rms_z = calc_rms(np.abs(z_r - z_n))
|
||||
# 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"
|
||||
|
||||
results[f'BH{bh}'] = {
|
||||
'3D_Vector': rms_3d,
|
||||
'X_Component': rms_x,
|
||||
'Y_Component': rms_y,
|
||||
'Z_Component': rms_z
|
||||
}
|
||||
terms2 = (delta_r2[valid_mask2] / r2_max[valid_mask2])**2
|
||||
rms_bh2 = np.sqrt(np.mean(terms2)) * 100
|
||||
|
||||
# 获取 BH1 和 BH2 中的最大误差
|
||||
max_rms = {
|
||||
'3D_Vector': max(results['BH1']['3D_Vector'], results['BH2']['3D_Vector']),
|
||||
'X_Component': max(results['BH1']['X_Component'], results['BH2']['X_Component']),
|
||||
'Y_Component': max(results['BH1']['Y_Component'], results['BH2']['Y_Component']),
|
||||
'Z_Component': max(results['BH1']['Z_Component'], results['BH2']['Z_Component'])
|
||||
}
|
||||
# Final RMS is the maximum of BH1 and BH2
|
||||
rms_final = max(rms_bh1, rms_bh2)
|
||||
|
||||
return rms_final, None
|
||||
|
||||
return max_rms, None
|
||||
|
||||
def analyze_constraint_violation(constraint_data, n_levels=9):
|
||||
"""
|
||||
@@ -277,32 +155,34 @@ def analyze_constraint_violation(constraint_data, n_levels=9):
|
||||
|
||||
|
||||
def print_header():
|
||||
"""Print report header"""
|
||||
print("\n" + Color.BLUE + Color.BOLD + "=" * 65 + Color.RESET)
|
||||
print(Color.BOLD + " AMSS-NCKU GW150914 Comprehensive Regression Test" + 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_dict, error, threshold=1.0):
|
||||
print(f"\n{Color.BOLD}1. RMS Error Analysis (Maximums of BH1 & BH2){Color.RESET}")
|
||||
print("-" * 65)
|
||||
|
||||
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
|
||||
|
||||
all_passed = True
|
||||
print(f" Requirement: < {threshold}%\n")
|
||||
passed = rms_rel < threshold
|
||||
|
||||
for key, val in rms_dict.items():
|
||||
passed = val < threshold
|
||||
all_passed = all_passed and passed
|
||||
status = get_status_text(passed)
|
||||
print(f" {key:15}: {val:8.4f}% | Status: {status}")
|
||||
print(f" RMS relative error: {rms_rel:.4f}%")
|
||||
print(f" Requirement: < {threshold}%")
|
||||
print(f" Status: {get_status_text(passed)}")
|
||||
|
||||
return passed
|
||||
|
||||
return all_passed
|
||||
|
||||
def print_constraint_results(results, threshold=2.0):
|
||||
"""Print constraint violation results"""
|
||||
print(f"\n{Color.BOLD}2. ADM Constraint Violation Analysis (Grid Level 0){Color.RESET}")
|
||||
print("-" * 65)
|
||||
print("-" * 45)
|
||||
|
||||
names = ['Ham', 'Px', 'Py', 'Pz', 'Gx', 'Gy', 'Gz']
|
||||
for i, name in enumerate(names):
|
||||
@@ -319,45 +199,19 @@ def print_constraint_results(results, threshold=2.0):
|
||||
return passed
|
||||
|
||||
|
||||
def print_figure_results(results, threshold_percent=0.001):
|
||||
print(f"\n{Color.BOLD}3. Figure Pixel Comparison (PDF Rasterization){Color.RESET}")
|
||||
print("-" * 65)
|
||||
print(f" Requirement: < {threshold_percent:.3f}% differing pixels\n")
|
||||
|
||||
all_passed = True
|
||||
for result in results:
|
||||
passed = result["passed"]
|
||||
all_passed = all_passed and passed
|
||||
status = get_status_text(passed)
|
||||
print(f" {result['name']:32}: {result['diff_percent']:10.6f}% | Status: {status}")
|
||||
|
||||
if result["pages_ref"] != result["pages_target"]:
|
||||
print(f" {'':32} pages(ref/target): {result['pages_ref']}/{result['pages_target']}")
|
||||
|
||||
return all_passed
|
||||
|
||||
|
||||
def print_figure_error(error_message):
|
||||
print(f"\n{Color.BOLD}3. Figure Pixel Comparison (PDF Rasterization){Color.RESET}")
|
||||
print("-" * 65)
|
||||
print(f" {Color.RED}Error: {error_message}{Color.RESET}")
|
||||
return False
|
||||
|
||||
|
||||
def print_summary(rms_passed, constraint_passed, figure_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 and figure_passed
|
||||
all_passed = rms_passed and constraint_passed
|
||||
|
||||
res_rms = get_status_text(rms_passed)
|
||||
res_con = get_status_text(constraint_passed)
|
||||
res_fig = get_status_text(figure_passed)
|
||||
|
||||
print(f" [1] Comprehensive RMS check: {res_rms}")
|
||||
print(f" [1] RMS trajectory check: {res_rms}")
|
||||
print(f" [2] ADM constraint check: {res_con}")
|
||||
print(f" [3] Figure pixel comparison: {res_fig}")
|
||||
|
||||
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}")
|
||||
@@ -365,58 +219,61 @@ def print_summary(rms_passed, constraint_passed, figure_passed):
|
||||
|
||||
return all_passed
|
||||
|
||||
|
||||
def main():
|
||||
# Determine target (optimized) output directory
|
||||
if len(sys.argv) > 1:
|
||||
target_dir = sys.argv[1]
|
||||
else:
|
||||
script_dir = os.path.dirname(os.path.abspath(__file__))
|
||||
target_dir = os.path.join(script_dir, "GW150914/AMSS_NCKU_output")
|
||||
|
||||
# Determine reference (baseline) directory
|
||||
script_dir = os.path.dirname(os.path.abspath(__file__))
|
||||
reference_dir = os.path.join(script_dir, "GW150914-origin/AMSS_NCKU_output")
|
||||
target_figure_dir = resolve_figure_dir(target_dir)
|
||||
reference_figure_dir = os.path.join(script_dir, "GW150914-origin/figure")
|
||||
|
||||
# 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}")
|
||||
print(f"{Color.BOLD}Reference Figures: {Color.RESET} {Color.BLUE}{reference_figure_dir}{Color.RESET}")
|
||||
print(f"{Color.BOLD}Target Figures: {Color.RESET} {Color.BLUE}{target_figure_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)
|
||||
|
||||
# Output modified RMS results
|
||||
rms_dict, error = calculate_all_rms_errors(bh_data_ref, bh_data_target)
|
||||
rms_passed = print_rms_results(rms_dict, error)
|
||||
# Calculate RMS error
|
||||
rms_rel, error = calculate_rms_error(bh_data_ref, bh_data_target)
|
||||
rms_passed = print_rms_results(rms_rel, error)
|
||||
|
||||
# Output constraint results
|
||||
# Analyze constraint violation
|
||||
constraint_results = analyze_constraint_violation(constraint_data)
|
||||
constraint_passed = print_constraint_results(constraint_results)
|
||||
|
||||
try:
|
||||
figure_results = compare_required_figures(reference_figure_dir, target_figure_dir)
|
||||
figure_passed = print_figure_results(figure_results)
|
||||
except (FileNotFoundError, RuntimeError) as exc:
|
||||
figure_passed = print_figure_error(str(exc))
|
||||
# Print summary
|
||||
all_passed = print_summary(rms_passed, constraint_passed)
|
||||
|
||||
all_passed = print_summary(rms_passed, constraint_passed, figure_passed)
|
||||
# Return exit code
|
||||
sys.exit(0 if all_passed else 1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
710
AMSS_NCKU_source/ABE.optrpt
Normal file
710
AMSS_NCKU_source/ABE.optrpt
Normal file
@@ -0,0 +1,710 @@
|
||||
Begin optimization report for: __cxx_global_var_init
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, int, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::map()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, int, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::~map()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: __cxx_global_var_init.1
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, double, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::map()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, double, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::~map()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: __cxx_global_var_init.2
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::map()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::~map()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: main
|
||||
|
||||
LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (1947, 7)
|
||||
LOOP END
|
||||
|
||||
LOOP BEGIN at ABE.C (125, 13)
|
||||
LOOP END
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::allocator<char>::allocator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::basic_string<std::allocator<char>>(char const*, std::allocator<char> const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__new_allocator<char>::~__new_allocator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::insert(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>::pair<char const (&) [9], std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>&, true>(char const (&) [9], std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>::~pair()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::~basic_string()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_Rb_tree_iterator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::basic_string()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::find(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&)
|
||||
|
||||
LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (1947, 7)
|
||||
LOOP END
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::operator!=(std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>> const&, std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>> const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::end()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::operator->() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::operator=(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::c_str() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ostream<char, std::char_traits<char>>& std::operator<<<std::char_traits<char>>(std::basic_ostream<char, std::char_traits<char>>&, char const*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::ostream::operator<<(std::ostream& (*)(std::ostream&))
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ostream<char, std::char_traits<char>>& std::endl<char, std::char_traits<char>>(std::basic_ostream<char, std::char_traits<char>>&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ifstream<char, std::char_traits<char>>::basic_ifstream(char const*, std::_Ios_Openmode)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ios<char, std::char_traits<char>>::good() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::istream::getline(char*, long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::operator=(char const*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::basic_string(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: bool std::operator==<char, std::char_traits<char>, std::allocator<char>>(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&, char const*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: atoi
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: atof
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ifstream<char, std::char_traits<char>>::close()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>::pair<char const (&) [11], std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>&, true>(char const (&) [11], std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ifstream<char, std::char_traits<char>>::~basic_ifstream()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ofstream<char, std::char_traits<char>>::basic_ofstream()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ofstream<char, std::char_traits<char>>::open(char const*, std::_Ios_Openmode)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ofstream<char, std::char_traits<char>>::close()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ofstream<char, std::char_traits<char>>::~basic_ofstream()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::ostream::operator<<(double)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_Rb_tree()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_Rb_tree_impl<std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, true>::_Rb_tree_impl()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::allocator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree_key_compare<std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_Rb_tree_key_compare()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree_header::_Rb_tree_header()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::__new_allocator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree_header::_M_reset()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: __clang_call_terminate
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::~_Rb_tree()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_M_erase(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>*)
|
||||
|
||||
LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (1930, 7)
|
||||
remark #15521: Loop was not vectorized: loop control variable was not identified. Explicitly compute the iteration count before executing the loop or try using canonical loop form from OpenMP specification
|
||||
remark #25478: While loop unrolled by 2
|
||||
LOOP END
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_M_begin()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::~__new_allocator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_S_right(std::_Rb_tree_node_base*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_S_left(std::_Rb_tree_node_base*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_M_drop_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_M_destroy_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_M_put_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: void std::allocator_traits<std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>>::destroy<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>(std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>&, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_M_get_Node_allocator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>::_M_valptr()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: void std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::destroy<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>::~pair()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: __gnu_cxx::__aligned_membuf<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>::_M_ptr()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: __gnu_cxx::__aligned_membuf<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>::_M_addr()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::allocator_traits<std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>>::deallocate(std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>&, std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>*, unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::deallocate(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>*, unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, int>>>::_M_mbegin() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_Rb_tree()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_Rb_tree_impl<std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, true>::_Rb_tree_impl()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::allocator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::__new_allocator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::~_Rb_tree()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_M_erase(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>*)
|
||||
|
||||
LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (1930, 7)
|
||||
remark #15521: Loop was not vectorized: loop control variable was not identified. Explicitly compute the iteration count before executing the loop or try using canonical loop form from OpenMP specification
|
||||
remark #25478: While loop unrolled by 2
|
||||
LOOP END
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_M_begin()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::~__new_allocator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_S_right(std::_Rb_tree_node_base*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_S_left(std::_Rb_tree_node_base*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_M_drop_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_M_destroy_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_M_put_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: void std::allocator_traits<std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>>::destroy<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>(std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>&, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_M_get_Node_allocator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>::_M_valptr()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: void std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::destroy<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>::~pair()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: __gnu_cxx::__aligned_membuf<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>::_M_ptr()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: __gnu_cxx::__aligned_membuf<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>::_M_addr()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::allocator_traits<std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>>::deallocate(std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>&, std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>*, unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::deallocate(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>*, unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, double>>>::_M_mbegin() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_Rb_tree()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_Rb_tree_impl<std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, true>::_Rb_tree_impl()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::allocator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::__new_allocator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::~_Rb_tree()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_erase(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*)
|
||||
|
||||
LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (1930, 7)
|
||||
remark #15521: Loop was not vectorized: loop control variable was not identified. Explicitly compute the iteration count before executing the loop or try using canonical loop form from OpenMP specification
|
||||
LOOP END
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_begin()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::~__new_allocator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_S_right(std::_Rb_tree_node_base*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_S_left(std::_Rb_tree_node_base*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_drop_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_destroy_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_put_node(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: void std::allocator_traits<std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>>::destroy<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>(std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>&, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_get_Node_allocator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_M_valptr()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: void std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::destroy<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: __gnu_cxx::__aligned_membuf<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_M_ptr()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: __gnu_cxx::__aligned_membuf<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_M_addr()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::allocator_traits<std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>>::deallocate(std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>&, std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*, unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::deallocate(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*, unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_mbegin() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_data() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_local_data()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_Alloc_hider::_Alloc_hider(char*, std::allocator<char>&&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_init_local_buf()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_set_length(unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__ptr_traits_ptr_to<char*, char, false>::pointer_to(char&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__new_allocator<char>::__new_allocator(std::__new_allocator<char> const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_length(unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::char_traits<char>::assign(char&, char const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__new_allocator<char>::__new_allocator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_dispose()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_Alloc_hider::~_Alloc_hider()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_is_local() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_destroy(unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_local_data() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__ptr_traits_ptr_to<char const*, char const, false>::pointer_to(char const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::allocator_traits<std::allocator<char>>::deallocate(std::allocator<char>&, char*, unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_get_allocator()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__new_allocator<char>::deallocate(char*, unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_Alloc_hider::_Alloc_hider(char*, std::allocator<char> const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::char_traits<char>::length(char const*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_construct<char const*>(char const*, char const*, std::forward_iterator_tag)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::iterator_traits<char const*>::difference_type std::distance<char const*>(char const*, char const*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_data(char*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_capacity(unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_construct<char const*>(char const*, char const*, std::forward_iterator_tag)::_Guard::_Guard(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_S_copy_chars(char*, char const*, char const*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_construct<char const*>(char const*, char const*, std::forward_iterator_tag)::_Guard::~_Guard()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::iterator_traits<char const*>::difference_type std::__distance<char const*>(char const*, char const*, std::random_access_iterator_tag)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::iterator_traits<char const*>::iterator_category std::__iterator_category<char const*>(char const* const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_S_copy(char*, char const*, unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::char_traits<char>::copy(char*, char const*, unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: __gnu_cxx::__alloc_traits<std::allocator<char>, char>::_S_select_on_copy(std::allocator<char> const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_get_allocator() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_construct<char*>(char*, char*, std::forward_iterator_tag)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::length() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::allocator_traits<std::allocator<char>>::select_on_container_copy_construction(std::allocator<char> const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::allocator<char>::allocator(std::allocator<char> const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::iterator_traits<char*>::difference_type std::distance<char*>(char*, char*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_construct<char*>(char*, char*, std::forward_iterator_tag)::_Guard::_Guard(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_S_copy_chars(char*, char*, char*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_construct<char*>(char*, char*, std::forward_iterator_tag)::_Guard::~_Guard()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::iterator_traits<char*>::difference_type std::__distance<char*>(char*, char*, std::random_access_iterator_tag)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::iterator_traits<char*>::iterator_category std::__iterator_category<char*>(char* const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::pair<std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, bool> std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_insert_unique<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&)
|
||||
|
||||
LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (2113, 7)
|
||||
LOOP END
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_get_insert_unique_pos(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&)
|
||||
|
||||
LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (2113, 7)
|
||||
LOOP END
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::operator()(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&) const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_Alloc_node::_Alloc_node(std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>> std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_insert_<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_Alloc_node>(std::_Rb_tree_node_base*, std::_Rb_tree_node_base*, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&, std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_Alloc_node&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::pair<std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, bool>::pair<std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, bool, true>(std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>&&, bool&&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_Rb_tree_iterator(std::_Rb_tree_node_base*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_end()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>::operator()(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&) const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_S_key(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>> const*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::operator==(std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>> const&, std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>> const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::begin()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::pair<std::_Rb_tree_node_base*, std::_Rb_tree_node_base*>::pair<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*&, std::_Rb_tree_node_base*&, true>(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*&, std::_Rb_tree_node_base*&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree_iterator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::operator--()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_S_key(std::_Rb_tree_node_base const*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::pair<std::_Rb_tree_node_base*, std::_Rb_tree_node_base*>::pair<std::_Rb_tree_node_base*, std::_Rb_tree_node_base*, true>(std::_Rb_tree_node_base* const&, std::_Rb_tree_node_base* const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: bool std::operator<<char, std::char_traits<char>, std::allocator<char>>(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::compare(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&) const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::size() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: unsigned long const& std::min<unsigned long>(unsigned long const&, unsigned long const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::char_traits<char>::compare(char const*, char const*, unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::data() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_S_compare(unsigned long, unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::operator()(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>> const&) const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_M_valptr() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: __gnu_cxx::__aligned_membuf<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_M_ptr() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: __gnu_cxx::__aligned_membuf<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>::_M_addr() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>* std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_Alloc_node::operator()<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&) const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>* std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_create_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_get_node()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: void std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_construct_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::allocator_traits<std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>>::allocate(std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>&, unsigned long)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::allocate(unsigned long, void const*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_max_size() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: void std::allocator_traits<std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>>::construct<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>(std::allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>&, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>*, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: void std::__new_allocator<std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::construct<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>*, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>::pair(std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>&&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::basic_string(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>&&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::_M_use_local_data()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::find(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&)
|
||||
|
||||
LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (1947, 7)
|
||||
LOOP END
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::_M_lower_bound(std::_Rb_tree_node<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>*, std::_Rb_tree_node_base*, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&)
|
||||
|
||||
LOOP BEGIN at /usr/lib/gcc/x86_64-redhat-linux/14/../../../../include/c++/14/bits/stl_tree.h (1947, 7)
|
||||
LOOP END
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::_Rb_tree<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::_Select1st<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>>>>::end()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::assign(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ios<char, std::char_traits<char>>::setstate(std::_Ios_Iostate)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::operator|(std::_Ios_Iostate, std::_Ios_Iostate)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ios<char, std::char_traits<char>>::rdstate() const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ostream<char, std::char_traits<char>>& std::flush<char, std::char_traits<char>>(std::basic_ostream<char, std::char_traits<char>>&)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ios<char, std::char_traits<char>>::widen(char) const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::ctype<char> const& std::__check_facet<std::ctype<char>>(std::ctype<char> const*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::ctype<char>::widen(char) const
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ios<char, std::char_traits<char>>::basic_ios()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_istream<char, std::char_traits<char>>::basic_istream()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ifstream<char, std::char_traits<char>>::open(char const*, std::_Ios_Openmode)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_filebuf<char, std::char_traits<char>>::~basic_filebuf()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_istream<char, std::char_traits<char>>::~basic_istream()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::operator|(std::_Ios_Openmode, std::_Ios_Openmode)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_streambuf<char, std::char_traits<char>>::~basic_streambuf()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ifstream<char, std::char_traits<char>>::~basic_ifstream()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: virtual thunk to std::basic_ifstream<char, std::char_traits<char>>::~basic_ifstream()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>>::assign(char const*)
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ostream<char, std::char_traits<char>>::basic_ostream()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ostream<char, std::char_traits<char>>::~basic_ostream()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: std::basic_ofstream<char, std::char_traits<char>>::~basic_ofstream()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: virtual thunk to std::basic_ofstream<char, std::char_traits<char>>::~basic_ofstream()
|
||||
=================================================================
|
||||
|
||||
Begin optimization report for: _GLOBAL__sub_I_ABE.C
|
||||
=================================================================
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,255 +0,0 @@
|
||||
#include "tool.h"
|
||||
/*
|
||||
* 你需要提供 symmetry_bd 的 C 版本（或 Fortran 绑到 C 的接口）。
|
||||
* Fortran: call symmetry_bd(3,ex,f,fh,SoA)
|
||||
*
|
||||
* 约定：
|
||||
* nghost = 3
|
||||
* ex[3] = {ex1,ex2,ex3}
|
||||
* f = 原始网格 (ex1*ex2*ex3)
|
||||
* fh = 扩展网格 ((ex1+3)*(ex2+3)*(ex3+3))，对应 Fortran 的 (-2:ex1, ...)
|
||||
* SoA[3] = 输入参数
|
||||
*/
|
||||
void lopsided(const int ex[3],
|
||||
const double *X, const double *Y, const double *Z,
|
||||
const double *f, double *f_rhs,
|
||||
const double *Sfx, const double *Sfy, const double *Sfz,
|
||||
int Symmetry, const double SoA[3])
|
||||
{
|
||||
const double ZEO = 0.0, ONE = 1.0, F3 = 3.0;
|
||||
const double TWO = 2.0, F6 = 6.0, F18 = 18.0;
|
||||
const double F12 = 12.0, F10 = 10.0, EIT = 8.0;
|
||||
|
||||
const int NO_SYMM = 0, EQ_SYMM = 1, OCTANT = 2;
|
||||
(void)OCTANT; // 这里和 Fortran 一样只是定义了不用也没关系
|
||||
|
||||
const int ex1 = ex[0], ex2 = ex[1], ex3 = ex[2];
|
||||
|
||||
// 对应 Fortran: dX = X(2)-X(1) （Fortran 1-based）
|
||||
// C: X[1]-X[0]
|
||||
const double dX = X[1] - X[0];
|
||||
const double dY = Y[1] - Y[0];
|
||||
const double dZ = Z[1] - Z[0];
|
||||
|
||||
const double d12dx = ONE / F12 / dX;
|
||||
const double d12dy = ONE / F12 / dY;
|
||||
const double d12dz = ONE / F12 / dZ;
|
||||
|
||||
// Fortran 里算了 d2dx/d2dy/d2dz 但本 subroutine 里没用到（保持一致也算出来）
|
||||
const double d2dx = ONE / TWO / dX;
|
||||
const double d2dy = ONE / TWO / dY;
|
||||
const double d2dz = ONE / TWO / dZ;
|
||||
(void)d2dx; (void)d2dy; (void)d2dz;
|
||||
|
||||
// Fortran:
|
||||
// imax = ex(1); jmax = ex(2); kmax = ex(3)
|
||||
const int imaxF = ex1;
|
||||
const int jmaxF = ex2;
|
||||
const int kmaxF = ex3;
|
||||
|
||||
// Fortran:
|
||||
// imin=jmin=kmin=1; 若满足对称条件则设为 -2
|
||||
int iminF = 1, jminF = 1, kminF = 1;
|
||||
if (Symmetry > NO_SYMM && fabs(Z[0]) < dZ) kminF = -2;
|
||||
if (Symmetry > EQ_SYMM && fabs(X[0]) < dX) iminF = -2;
|
||||
if (Symmetry > EQ_SYMM && fabs(Y[0]) < dY) jminF = -2;
|
||||
|
||||
// 分配 fh：大小 (ex1+3)*(ex2+3)*(ex3+3)
|
||||
const size_t nx = (size_t)ex1 + 3;
|
||||
const size_t ny = (size_t)ex2 + 3;
|
||||
const size_t nz = (size_t)ex3 + 3;
|
||||
const size_t fh_size = nx * ny * nz;
|
||||
|
||||
double *fh = (double*)malloc(fh_size * sizeof(double));
|
||||
if (!fh) return; // 内存不足：直接返回（你也可以改成 abort/报错）
|
||||
|
||||
// Fortran: call symmetry_bd(3,ex,f,fh,SoA)
|
||||
symmetry_bd(3, ex, f, fh, SoA);
|
||||
|
||||
/*
|
||||
* Fortran 主循环：
|
||||
* do k=1,ex(3)-1
|
||||
* do j=1,ex(2)-1
|
||||
* do i=1,ex(1)-1
|
||||
*
|
||||
* 转成 C 0-based：
|
||||
* k0 = 0..ex3-2, j0 = 0..ex2-2, i0 = 0..ex1-2
|
||||
*
|
||||
* 并且 Fortran 里的 i/j/k 在 fh 访问时，仍然是 Fortran 索引值：
|
||||
* iF=i0+1, jF=j0+1, kF=k0+1
|
||||
*/
|
||||
for (int k0 = 0; k0 <= ex3 - 2; ++k0) {
|
||||
const int kF = k0 + 1;
|
||||
for (int j0 = 0; j0 <= ex2 - 2; ++j0) {
|
||||
const int jF = j0 + 1;
|
||||
for (int i0 = 0; i0 <= ex1 - 2; ++i0) {
|
||||
const int iF = i0 + 1;
|
||||
|
||||
const size_t p = idx_ex(i0, j0, k0, ex);
|
||||
|
||||
// ---------------- x direction ----------------
|
||||
const double sfx = Sfx[p];
|
||||
if (sfx > ZEO) {
|
||||
// Fortran: if(i+3 <= imax)
|
||||
// iF+3 <= ex1 <=> i0+4 <= ex1 <=> i0 <= ex1-4
|
||||
if (i0 <= ex1 - 4) {
|
||||
f_rhs[p] += sfx * d12dx *
|
||||
(-F3 * fh[idx_fh_F(iF - 1, jF, kF, ex)]
|
||||
-F10 * fh[idx_fh_F(iF , jF, kF, ex)]
|
||||
+F18 * fh[idx_fh_F(iF + 1, jF, kF, ex)]
|
||||
-F6 * fh[idx_fh_F(iF + 2, jF, kF, ex)]
|
||||
+ fh[idx_fh_F(iF + 3, jF, kF, ex)]);
|
||||
}
|
||||
// elseif(i+2 <= imax) <=> i0 <= ex1-3
|
||||
else if (i0 <= ex1 - 3) {
|
||||
f_rhs[p] += sfx * d12dx *
|
||||
( fh[idx_fh_F(iF - 2, jF, kF, ex)]
|
||||
-EIT * fh[idx_fh_F(iF - 1, jF, kF, ex)]
|
||||
+EIT * fh[idx_fh_F(iF + 1, jF, kF, ex)]
|
||||
- fh[idx_fh_F(iF + 2, jF, kF, ex)]);
|
||||
}
|
||||
// elseif(i+1 <= imax) <=> i0 <= ex1-2（循环里总成立）
|
||||
else if (i0 <= ex1 - 2) {
|
||||
f_rhs[p] -= sfx * d12dx *
|
||||
(-F3 * fh[idx_fh_F(iF + 1, jF, kF, ex)]
|
||||
-F10 * fh[idx_fh_F(iF , jF, kF, ex)]
|
||||
+F18 * fh[idx_fh_F(iF - 1, jF, kF, ex)]
|
||||
-F6 * fh[idx_fh_F(iF - 2, jF, kF, ex)]
|
||||
+ fh[idx_fh_F(iF - 3, jF, kF, ex)]);
|
||||
}
|
||||
} else if (sfx < ZEO) {
|
||||
// Fortran: if(i-3 >= imin)
|
||||
// (iF-3) >= iminF <=> (i0-2) >= iminF
|
||||
if ((i0 - 2) >= iminF) {
|
||||
f_rhs[p] -= sfx * d12dx *
|
||||
(-F3 * fh[idx_fh_F(iF + 1, jF, kF, ex)]
|
||||
-F10 * fh[idx_fh_F(iF , jF, kF, ex)]
|
||||
+F18 * fh[idx_fh_F(iF - 1, jF, kF, ex)]
|
||||
-F6 * fh[idx_fh_F(iF - 2, jF, kF, ex)]
|
||||
+ fh[idx_fh_F(iF - 3, jF, kF, ex)]);
|
||||
}
|
||||
// elseif(i-2 >= imin) <=> (i0-1) >= iminF
|
||||
else if ((i0 - 1) >= iminF) {
|
||||
f_rhs[p] += sfx * d12dx *
|
||||
( fh[idx_fh_F(iF - 2, jF, kF, ex)]
|
||||
-EIT * fh[idx_fh_F(iF - 1, jF, kF, ex)]
|
||||
+EIT * fh[idx_fh_F(iF + 1, jF, kF, ex)]
|
||||
- fh[idx_fh_F(iF + 2, jF, kF, ex)]);
|
||||
}
|
||||
// elseif(i-1 >= imin) <=> i0 >= iminF
|
||||
else if (i0 >= iminF) {
|
||||
f_rhs[p] += sfx * d12dx *
|
||||
(-F3 * fh[idx_fh_F(iF - 1, jF, kF, ex)]
|
||||
-F10 * fh[idx_fh_F(iF , jF, kF, ex)]
|
||||
+F18 * fh[idx_fh_F(iF + 1, jF, kF, ex)]
|
||||
-F6 * fh[idx_fh_F(iF + 2, jF, kF, ex)]
|
||||
+ fh[idx_fh_F(iF + 3, jF, kF, ex)]);
|
||||
}
|
||||
}
|
||||
|
||||
// ---------------- y direction ----------------
|
||||
const double sfy = Sfy[p];
|
||||
if (sfy > ZEO) {
|
||||
// jF+3 <= ex2 <=> j0+4 <= ex2 <=> j0 <= ex2-4
|
||||
if (j0 <= ex2 - 4) {
|
||||
f_rhs[p] += sfy * d12dy *
|
||||
(-F3 * fh[idx_fh_F(iF, jF - 1, kF, ex)]
|
||||
-F10 * fh[idx_fh_F(iF, jF , kF, ex)]
|
||||
+F18 * fh[idx_fh_F(iF, jF + 1, kF, ex)]
|
||||
-F6 * fh[idx_fh_F(iF, jF + 2, kF, ex)]
|
||||
+ fh[idx_fh_F(iF, jF + 3, kF, ex)]);
|
||||
} else if (j0 <= ex2 - 3) {
|
||||
f_rhs[p] += sfy * d12dy *
|
||||
( fh[idx_fh_F(iF, jF - 2, kF, ex)]
|
||||
-EIT * fh[idx_fh_F(iF, jF - 1, kF, ex)]
|
||||
+EIT * fh[idx_fh_F(iF, jF + 1, kF, ex)]
|
||||
- fh[idx_fh_F(iF, jF + 2, kF, ex)]);
|
||||
} else if (j0 <= ex2 - 2) {
|
||||
f_rhs[p] -= sfy * d12dy *
|
||||
(-F3 * fh[idx_fh_F(iF, jF + 1, kF, ex)]
|
||||
-F10 * fh[idx_fh_F(iF, jF , kF, ex)]
|
||||
+F18 * fh[idx_fh_F(iF, jF - 1, kF, ex)]
|
||||
-F6 * fh[idx_fh_F(iF, jF - 2, kF, ex)]
|
||||
+ fh[idx_fh_F(iF, jF - 3, kF, ex)]);
|
||||
}
|
||||
} else if (sfy < ZEO) {
|
||||
if ((j0 - 2) >= jminF) {
|
||||
f_rhs[p] -= sfy * d12dy *
|
||||
(-F3 * fh[idx_fh_F(iF, jF + 1, kF, ex)]
|
||||
-F10 * fh[idx_fh_F(iF, jF , kF, ex)]
|
||||
+F18 * fh[idx_fh_F(iF, jF - 1, kF, ex)]
|
||||
-F6 * fh[idx_fh_F(iF, jF - 2, kF, ex)]
|
||||
+ fh[idx_fh_F(iF, jF - 3, kF, ex)]);
|
||||
} else if ((j0 - 1) >= jminF) {
|
||||
f_rhs[p] += sfy * d12dy *
|
||||
( fh[idx_fh_F(iF, jF - 2, kF, ex)]
|
||||
-EIT * fh[idx_fh_F(iF, jF - 1, kF, ex)]
|
||||
+EIT * fh[idx_fh_F(iF, jF + 1, kF, ex)]
|
||||
- fh[idx_fh_F(iF, jF + 2, kF, ex)]);
|
||||
} else if (j0 >= jminF) {
|
||||
f_rhs[p] += sfy * d12dy *
|
||||
(-F3 * fh[idx_fh_F(iF, jF - 1, kF, ex)]
|
||||
-F10 * fh[idx_fh_F(iF, jF , kF, ex)]
|
||||
+F18 * fh[idx_fh_F(iF, jF + 1, kF, ex)]
|
||||
-F6 * fh[idx_fh_F(iF, jF + 2, kF, ex)]
|
||||
+ fh[idx_fh_F(iF, jF + 3, kF, ex)]);
|
||||
}
|
||||
}
|
||||
|
||||
// ---------------- z direction ----------------
|
||||
const double sfz = Sfz[p];
|
||||
if (sfz > ZEO) {
|
||||
if (k0 <= ex3 - 4) {
|
||||
f_rhs[p] += sfz * d12dz *
|
||||
(-F3 * fh[idx_fh_F(iF, jF, kF - 1, ex)]
|
||||
-F10 * fh[idx_fh_F(iF, jF, kF , ex)]
|
||||
+F18 * fh[idx_fh_F(iF, jF, kF + 1, ex)]
|
||||
-F6 * fh[idx_fh_F(iF, jF, kF + 2, ex)]
|
||||
+ fh[idx_fh_F(iF, jF, kF + 3, ex)]);
|
||||
} else if (k0 <= ex3 - 3) {
|
||||
f_rhs[p] += sfz * d12dz *
|
||||
( fh[idx_fh_F(iF, jF, kF - 2, ex)]
|
||||
-EIT * fh[idx_fh_F(iF, jF, kF - 1, ex)]
|
||||
+EIT * fh[idx_fh_F(iF, jF, kF + 1, ex)]
|
||||
- fh[idx_fh_F(iF, jF, kF + 2, ex)]);
|
||||
} else if (k0 <= ex3 - 2) {
|
||||
f_rhs[p] -= sfz * d12dz *
|
||||
(-F3 * fh[idx_fh_F(iF, jF, kF + 1, ex)]
|
||||
-F10 * fh[idx_fh_F(iF, jF, kF , ex)]
|
||||
+F18 * fh[idx_fh_F(iF, jF, kF - 1, ex)]
|
||||
-F6 * fh[idx_fh_F(iF, jF, kF - 2, ex)]
|
||||
+ fh[idx_fh_F(iF, jF, kF - 3, ex)]);
|
||||
}
|
||||
} else if (sfz < ZEO) {
|
||||
if ((k0 - 2) >= kminF) {
|
||||
f_rhs[p] -= sfz * d12dz *
|
||||
(-F3 * fh[idx_fh_F(iF, jF, kF + 1, ex)]
|
||||
-F10 * fh[idx_fh_F(iF, jF, kF , ex)]
|
||||
+F18 * fh[idx_fh_F(iF, jF, kF - 1, ex)]
|
||||
-F6 * fh[idx_fh_F(iF, jF, kF - 2, ex)]
|
||||
+ fh[idx_fh_F(iF, jF, kF - 3, ex)]);
|
||||
} else if ((k0 - 1) >= kminF) {
|
||||
f_rhs[p] += sfz * d12dz *
|
||||
( fh[idx_fh_F(iF, jF, kF - 2, ex)]
|
||||
-EIT * fh[idx_fh_F(iF, jF, kF - 1, ex)]
|
||||
+EIT * fh[idx_fh_F(iF, jF, kF + 1, ex)]
|
||||
- fh[idx_fh_F(iF, jF, kF + 2, ex)]);
|
||||
} else if (k0 >= kminF) {
|
||||
f_rhs[p] += sfz * d12dz *
|
||||
(-F3 * fh[idx_fh_F(iF, jF, kF - 1, ex)]
|
||||
-F10 * fh[idx_fh_F(iF, jF, kF , ex)]
|
||||
+F18 * fh[idx_fh_F(iF, jF, kF + 1, ex)]
|
||||
-F6 * fh[idx_fh_F(iF, jF, kF + 2, ex)]
|
||||
+ fh[idx_fh_F(iF, jF, kF + 3, ex)]);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
free(fh);
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -1,248 +0,0 @@
|
||||
#include "tool.h"
|
||||
|
||||
/*
|
||||
* Combined advection (lopsided) + KO dissipation (kodis).
|
||||
* Uses one shared symmetry_bd buffer per call.
|
||||
*/
|
||||
void lopsided_kodis(const int ex[3],
|
||||
const double *X, const double *Y, const double *Z,
|
||||
const double *f, double *f_rhs,
|
||||
const double *Sfx, const double *Sfy, const double *Sfz,
|
||||
int Symmetry, const double SoA[3], double eps)
|
||||
{
|
||||
const double ZEO = 0.0, ONE = 1.0, F3 = 3.0;
|
||||
const double F6 = 6.0, F18 = 18.0;
|
||||
const double F12 = 12.0, F10 = 10.0, EIT = 8.0;
|
||||
const double SIX = 6.0, FIT = 15.0, TWT = 20.0;
|
||||
const double cof = 64.0; // 2^6
|
||||
|
||||
const int NO_SYMM = 0, EQ_SYMM = 1;
|
||||
|
||||
const int ex1 = ex[0], ex2 = ex[1], ex3 = ex[2];
|
||||
|
||||
const double dX = X[1] - X[0];
|
||||
const double dY = Y[1] - Y[0];
|
||||
const double dZ = Z[1] - Z[0];
|
||||
|
||||
const double d12dx = ONE / F12 / dX;
|
||||
const double d12dy = ONE / F12 / dY;
|
||||
const double d12dz = ONE / F12 / dZ;
|
||||
|
||||
const int imaxF = ex1;
|
||||
const int jmaxF = ex2;
|
||||
const int kmaxF = ex3;
|
||||
|
||||
int iminF = 1, jminF = 1, kminF = 1;
|
||||
if (Symmetry > NO_SYMM && fabs(Z[0]) < dZ) kminF = -2;
|
||||
if (Symmetry > EQ_SYMM && fabs(X[0]) < dX) iminF = -2;
|
||||
if (Symmetry > EQ_SYMM && fabs(Y[0]) < dY) jminF = -2;
|
||||
|
||||
// fh for Fortran-style domain (-2:ex1,-2:ex2,-2:ex3)
|
||||
const size_t nx = (size_t)ex1 + 3;
|
||||
const size_t ny = (size_t)ex2 + 3;
|
||||
const size_t nz = (size_t)ex3 + 3;
|
||||
const size_t fh_size = nx * ny * nz;
|
||||
|
||||
double *fh = (double*)malloc(fh_size * sizeof(double));
|
||||
if (!fh) return;
|
||||
|
||||
symmetry_bd(3, ex, f, fh, SoA);
|
||||
|
||||
// Advection (same stencil logic as lopsided_c.C)
|
||||
for (int k0 = 0; k0 <= ex3 - 2; ++k0) {
|
||||
const int kF = k0 + 1;
|
||||
for (int j0 = 0; j0 <= ex2 - 2; ++j0) {
|
||||
const int jF = j0 + 1;
|
||||
for (int i0 = 0; i0 <= ex1 - 2; ++i0) {
|
||||
const int iF = i0 + 1;
|
||||
const size_t p = idx_ex(i0, j0, k0, ex);
|
||||
|
||||
const double sfx = Sfx[p];
|
||||
if (sfx > ZEO) {
|
||||
if (i0 <= ex1 - 4) {
|
||||
f_rhs[p] += sfx * d12dx *
|
||||
(-F3 * fh[idx_fh_F(iF - 1, jF, kF, ex)]
|
||||
-F10 * fh[idx_fh_F(iF , jF, kF, ex)]
|
||||
+F18 * fh[idx_fh_F(iF + 1, jF, kF, ex)]
|
||||
-F6 * fh[idx_fh_F(iF + 2, jF, kF, ex)]
|
||||
+ fh[idx_fh_F(iF + 3, jF, kF, ex)]);
|
||||
} else if (i0 <= ex1 - 3) {
|
||||
f_rhs[p] += sfx * d12dx *
|
||||
( fh[idx_fh_F(iF - 2, jF, kF, ex)]
|
||||
-EIT * fh[idx_fh_F(iF - 1, jF, kF, ex)]
|
||||
+EIT * fh[idx_fh_F(iF + 1, jF, kF, ex)]
|
||||
- fh[idx_fh_F(iF + 2, jF, kF, ex)]);
|
||||
} else if (i0 <= ex1 - 2) {
|
||||
f_rhs[p] -= sfx * d12dx *
|
||||
(-F3 * fh[idx_fh_F(iF + 1, jF, kF, ex)]
|
||||
-F10 * fh[idx_fh_F(iF , jF, kF, ex)]
|
||||
+F18 * fh[idx_fh_F(iF - 1, jF, kF, ex)]
|
||||
-F6 * fh[idx_fh_F(iF - 2, jF, kF, ex)]
|
||||
+ fh[idx_fh_F(iF - 3, jF, kF, ex)]);
|
||||
}
|
||||
} else if (sfx < ZEO) {
|
||||
if ((i0 - 2) >= iminF) {
|
||||
f_rhs[p] -= sfx * d12dx *
|
||||
(-F3 * fh[idx_fh_F(iF + 1, jF, kF, ex)]
|
||||
-F10 * fh[idx_fh_F(iF , jF, kF, ex)]
|
||||
+F18 * fh[idx_fh_F(iF - 1, jF, kF, ex)]
|
||||
-F6 * fh[idx_fh_F(iF - 2, jF, kF, ex)]
|
||||
+ fh[idx_fh_F(iF - 3, jF, kF, ex)]);
|
||||
} else if ((i0 - 1) >= iminF) {
|
||||
f_rhs[p] += sfx * d12dx *
|
||||
( fh[idx_fh_F(iF - 2, jF, kF, ex)]
|
||||
-EIT * fh[idx_fh_F(iF - 1, jF, kF, ex)]
|
||||
+EIT * fh[idx_fh_F(iF + 1, jF, kF, ex)]
|
||||
- fh[idx_fh_F(iF + 2, jF, kF, ex)]);
|
||||
} else if (i0 >= iminF) {
|
||||
f_rhs[p] += sfx * d12dx *
|
||||
(-F3 * fh[idx_fh_F(iF - 1, jF, kF, ex)]
|
||||
-F10 * fh[idx_fh_F(iF , jF, kF, ex)]
|
||||
+F18 * fh[idx_fh_F(iF + 1, jF, kF, ex)]
|
||||
-F6 * fh[idx_fh_F(iF + 2, jF, kF, ex)]
|
||||
+ fh[idx_fh_F(iF + 3, jF, kF, ex)]);
|
||||
}
|
||||
}
|
||||
|
||||
const double sfy = Sfy[p];
|
||||
if (sfy > ZEO) {
|
||||
if (j0 <= ex2 - 4) {
|
||||
f_rhs[p] += sfy * d12dy *
|
||||
(-F3 * fh[idx_fh_F(iF, jF - 1, kF, ex)]
|
||||
-F10 * fh[idx_fh_F(iF, jF , kF, ex)]
|
||||
+F18 * fh[idx_fh_F(iF, jF + 1, kF, ex)]
|
||||
-F6 * fh[idx_fh_F(iF, jF + 2, kF, ex)]
|
||||
+ fh[idx_fh_F(iF, jF + 3, kF, ex)]);
|
||||
} else if (j0 <= ex2 - 3) {
|
||||
f_rhs[p] += sfy * d12dy *
|
||||
( fh[idx_fh_F(iF, jF - 2, kF, ex)]
|
||||
-EIT * fh[idx_fh_F(iF, jF - 1, kF, ex)]
|
||||
+EIT * fh[idx_fh_F(iF, jF + 1, kF, ex)]
|
||||
- fh[idx_fh_F(iF, jF + 2, kF, ex)]);
|
||||
} else if (j0 <= ex2 - 2) {
|
||||
f_rhs[p] -= sfy * d12dy *
|
||||
(-F3 * fh[idx_fh_F(iF, jF + 1, kF, ex)]
|
||||
-F10 * fh[idx_fh_F(iF, jF , kF, ex)]
|
||||
+F18 * fh[idx_fh_F(iF, jF - 1, kF, ex)]
|
||||
-F6 * fh[idx_fh_F(iF, jF - 2, kF, ex)]
|
||||
+ fh[idx_fh_F(iF, jF - 3, kF, ex)]);
|
||||
}
|
||||
} else if (sfy < ZEO) {
|
||||
if ((j0 - 2) >= jminF) {
|
||||
f_rhs[p] -= sfy * d12dy *
|
||||
(-F3 * fh[idx_fh_F(iF, jF + 1, kF, ex)]
|
||||
-F10 * fh[idx_fh_F(iF, jF , kF, ex)]
|
||||
+F18 * fh[idx_fh_F(iF, jF - 1, kF, ex)]
|
||||
-F6 * fh[idx_fh_F(iF, jF - 2, kF, ex)]
|
||||
+ fh[idx_fh_F(iF, jF - 3, kF, ex)]);
|
||||
} else if ((j0 - 1) >= jminF) {
|
||||
f_rhs[p] += sfy * d12dy *
|
||||
( fh[idx_fh_F(iF, jF - 2, kF, ex)]
|
||||
-EIT * fh[idx_fh_F(iF, jF - 1, kF, ex)]
|
||||
+EIT * fh[idx_fh_F(iF, jF + 1, kF, ex)]
|
||||
- fh[idx_fh_F(iF, jF + 2, kF, ex)]);
|
||||
} else if (j0 >= jminF) {
|
||||
f_rhs[p] += sfy * d12dy *
|
||||
(-F3 * fh[idx_fh_F(iF, jF - 1, kF, ex)]
|
||||
-F10 * fh[idx_fh_F(iF, jF , kF, ex)]
|
||||
+F18 * fh[idx_fh_F(iF, jF + 1, kF, ex)]
|
||||
-F6 * fh[idx_fh_F(iF, jF + 2, kF, ex)]
|
||||
+ fh[idx_fh_F(iF, jF + 3, kF, ex)]);
|
||||
}
|
||||
}
|
||||
|
||||
const double sfz = Sfz[p];
|
||||
if (sfz > ZEO) {
|
||||
if (k0 <= ex3 - 4) {
|
||||
f_rhs[p] += sfz * d12dz *
|
||||
(-F3 * fh[idx_fh_F(iF, jF, kF - 1, ex)]
|
||||
-F10 * fh[idx_fh_F(iF, jF, kF , ex)]
|
||||
+F18 * fh[idx_fh_F(iF, jF, kF + 1, ex)]
|
||||
-F6 * fh[idx_fh_F(iF, jF, kF + 2, ex)]
|
||||
+ fh[idx_fh_F(iF, jF, kF + 3, ex)]);
|
||||
} else if (k0 <= ex3 - 3) {
|
||||
f_rhs[p] += sfz * d12dz *
|
||||
( fh[idx_fh_F(iF, jF, kF - 2, ex)]
|
||||
-EIT * fh[idx_fh_F(iF, jF, kF - 1, ex)]
|
||||
+EIT * fh[idx_fh_F(iF, jF, kF + 1, ex)]
|
||||
- fh[idx_fh_F(iF, jF, kF + 2, ex)]);
|
||||
} else if (k0 <= ex3 - 2) {
|
||||
f_rhs[p] -= sfz * d12dz *
|
||||
(-F3 * fh[idx_fh_F(iF, jF, kF + 1, ex)]
|
||||
-F10 * fh[idx_fh_F(iF, jF, kF , ex)]
|
||||
+F18 * fh[idx_fh_F(iF, jF, kF - 1, ex)]
|
||||
-F6 * fh[idx_fh_F(iF, jF, kF - 2, ex)]
|
||||
+ fh[idx_fh_F(iF, jF, kF - 3, ex)]);
|
||||
}
|
||||
} else if (sfz < ZEO) {
|
||||
if ((k0 - 2) >= kminF) {
|
||||
f_rhs[p] -= sfz * d12dz *
|
||||
(-F3 * fh[idx_fh_F(iF, jF, kF + 1, ex)]
|
||||
-F10 * fh[idx_fh_F(iF, jF, kF , ex)]
|
||||
+F18 * fh[idx_fh_F(iF, jF, kF - 1, ex)]
|
||||
-F6 * fh[idx_fh_F(iF, jF, kF - 2, ex)]
|
||||
+ fh[idx_fh_F(iF, jF, kF - 3, ex)]);
|
||||
} else if ((k0 - 1) >= kminF) {
|
||||
f_rhs[p] += sfz * d12dz *
|
||||
( fh[idx_fh_F(iF, jF, kF - 2, ex)]
|
||||
-EIT * fh[idx_fh_F(iF, jF, kF - 1, ex)]
|
||||
+EIT * fh[idx_fh_F(iF, jF, kF + 1, ex)]
|
||||
- fh[idx_fh_F(iF, jF, kF + 2, ex)]);
|
||||
} else if (k0 >= kminF) {
|
||||
f_rhs[p] += sfz * d12dz *
|
||||
(-F3 * fh[idx_fh_F(iF, jF, kF - 1, ex)]
|
||||
-F10 * fh[idx_fh_F(iF, jF, kF , ex)]
|
||||
+F18 * fh[idx_fh_F(iF, jF, kF + 1, ex)]
|
||||
-F6 * fh[idx_fh_F(iF, jF, kF + 2, ex)]
|
||||
+ fh[idx_fh_F(iF, jF, kF + 3, ex)]);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// KO dissipation (same domain restriction as kodiss_c.C)
|
||||
if (eps > ZEO) {
|
||||
const int i0_lo = (iminF + 2 > 0) ? iminF + 2 : 0;
|
||||
const int j0_lo = (jminF + 2 > 0) ? jminF + 2 : 0;
|
||||
const int k0_lo = (kminF + 2 > 0) ? kminF + 2 : 0;
|
||||
const int i0_hi = imaxF - 4; // inclusive
|
||||
const int j0_hi = jmaxF - 4;
|
||||
const int k0_hi = kmaxF - 4;
|
||||
|
||||
if (!(i0_lo > i0_hi || j0_lo > j0_hi || k0_lo > k0_hi)) {
|
||||
for (int k0 = k0_lo; k0 <= k0_hi; ++k0) {
|
||||
const int kF = k0 + 1;
|
||||
for (int j0 = j0_lo; j0 <= j0_hi; ++j0) {
|
||||
const int jF = j0 + 1;
|
||||
for (int i0 = i0_lo; i0 <= i0_hi; ++i0) {
|
||||
const int iF = i0 + 1;
|
||||
const size_t p = idx_ex(i0, j0, k0, ex);
|
||||
|
||||
const double Dx_term =
|
||||
((fh[idx_fh_F(iF - 3, jF, kF, ex)] + fh[idx_fh_F(iF + 3, jF, kF, ex)]) -
|
||||
SIX * (fh[idx_fh_F(iF - 2, jF, kF, ex)] + fh[idx_fh_F(iF + 2, jF, kF, ex)]) +
|
||||
FIT * (fh[idx_fh_F(iF - 1, jF, kF, ex)] + fh[idx_fh_F(iF + 1, jF, kF, ex)]) -
|
||||
TWT * fh[idx_fh_F(iF, jF, kF, ex)]) / dX;
|
||||
|
||||
const double Dy_term =
|
||||
((fh[idx_fh_F(iF, jF - 3, kF, ex)] + fh[idx_fh_F(iF, jF + 3, kF, ex)]) -
|
||||
SIX * (fh[idx_fh_F(iF, jF - 2, kF, ex)] + fh[idx_fh_F(iF, jF + 2, kF, ex)]) +
|
||||
FIT * (fh[idx_fh_F(iF, jF - 1, kF, ex)] + fh[idx_fh_F(iF, jF + 1, kF, ex)]) -
|
||||
TWT * fh[idx_fh_F(iF, jF, kF, ex)]) / dY;
|
||||
|
||||
const double Dz_term =
|
||||
((fh[idx_fh_F(iF, jF, kF - 3, ex)] + fh[idx_fh_F(iF, jF, kF + 3, ex)]) -
|
||||
SIX * (fh[idx_fh_F(iF, jF, kF - 2, ex)] + fh[idx_fh_F(iF, jF, kF + 2, ex)]) +
|
||||
FIT * (fh[idx_fh_F(iF, jF, kF - 1, ex)] + fh[idx_fh_F(iF, jF, kF + 1, ex)]) -
|
||||
TWT * fh[idx_fh_F(iF, jF, kF, ex)]) / dZ;
|
||||
|
||||
f_rhs[p] += (eps / cof) * (Dx_term + Dy_term + Dz_term);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
free(fh);
|
||||
}
|
||||
@@ -1,332 +0,0 @@
|
||||
#include "tool.h"
|
||||
void fdderivs(const int ex[3],
|
||||
const double *f,
|
||||
double *fxx, double *fxy, double *fxz,
|
||||
double *fyy, double *fyz, double *fzz,
|
||||
const double *X, const double *Y, const double *Z,
|
||||
double SYM1, double SYM2, double SYM3,
|
||||
int Symmetry, int onoff)
|
||||
{
|
||||
(void)onoff;
|
||||
|
||||
const int NO_SYMM = 0, EQ_SYMM = 1;
|
||||
const double ZEO = 0.0, ONE = 1.0, TWO = 2.0;
|
||||
const double F1o4 = 2.5e-1; // 1/4
|
||||
const double F8 = 8.0;
|
||||
const double F16 = 16.0;
|
||||
const double F30 = 30.0;
|
||||
const double F1o12 = ONE / 12.0;
|
||||
const double F1o144 = ONE / 144.0;
|
||||
|
||||
const int ex1 = ex[0], ex2 = ex[1], ex3 = ex[2];
|
||||
|
||||
const double dX = X[1] - X[0];
|
||||
const double dY = Y[1] - Y[0];
|
||||
const double dZ = Z[1] - Z[0];
|
||||
|
||||
const int imaxF = ex1;
|
||||
const int jmaxF = ex2;
|
||||
const int kmaxF = ex3;
|
||||
|
||||
int iminF = 1, jminF = 1, kminF = 1;
|
||||
if (Symmetry > NO_SYMM && fabs(Z[0]) < dZ) kminF = -1;
|
||||
if (Symmetry > EQ_SYMM && fabs(X[0]) < dX) iminF = -1;
|
||||
if (Symmetry > EQ_SYMM && fabs(Y[0]) < dY) jminF = -1;
|
||||
|
||||
const double SoA[3] = { SYM1, SYM2, SYM3 };
|
||||
|
||||
/* fh: (ex1+2)*(ex2+2)*(ex3+2) because ord=2 */
|
||||
const size_t nx = (size_t)ex1 + 2;
|
||||
const size_t ny = (size_t)ex2 + 2;
|
||||
const size_t nz = (size_t)ex3 + 2;
|
||||
const size_t fh_size = nx * ny * nz;
|
||||
|
||||
static double *fh = NULL;
|
||||
static size_t cap = 0;
|
||||
|
||||
if (fh_size > cap) {
|
||||
free(fh);
|
||||
fh = (double*)aligned_alloc(64, fh_size * sizeof(double));
|
||||
cap = fh_size;
|
||||
}
|
||||
// double *fh = (double*)malloc(fh_size * sizeof(double));
|
||||
if (!fh) return;
|
||||
|
||||
symmetry_bd(2, ex, f, fh, SoA);
|
||||
|
||||
/* 系数：按 Fortran 原式 */
|
||||
const double Sdxdx = ONE / (dX * dX);
|
||||
const double Sdydy = ONE / (dY * dY);
|
||||
const double Sdzdz = ONE / (dZ * dZ);
|
||||
|
||||
const double Fdxdx = F1o12 / (dX * dX);
|
||||
const double Fdydy = F1o12 / (dY * dY);
|
||||
const double Fdzdz = F1o12 / (dZ * dZ);
|
||||
|
||||
const double Sdxdy = F1o4 / (dX * dY);
|
||||
const double Sdxdz = F1o4 / (dX * dZ);
|
||||
const double Sdydz = F1o4 / (dY * dZ);
|
||||
|
||||
const double Fdxdy = F1o144 / (dX * dY);
|
||||
const double Fdxdz = F1o144 / (dX * dZ);
|
||||
const double Fdydz = F1o144 / (dY * dZ);
|
||||
|
||||
/* 只清零不被主循环覆盖的边界面 */
|
||||
{
|
||||
/* 高边界：k0=ex3-1 */
|
||||
for (int j0 = 0; j0 < ex2; ++j0)
|
||||
for (int i0 = 0; i0 < ex1; ++i0) {
|
||||
const size_t p = idx_ex(i0, j0, ex3 - 1, ex);
|
||||
fxx[p]=ZEO; fyy[p]=ZEO; fzz[p]=ZEO;
|
||||
fxy[p]=ZEO; fxz[p]=ZEO; fyz[p]=ZEO;
|
||||
}
|
||||
/* 高边界：j0=ex2-1 */
|
||||
for (int k0 = 0; k0 < ex3 - 1; ++k0)
|
||||
for (int i0 = 0; i0 < ex1; ++i0) {
|
||||
const size_t p = idx_ex(i0, ex2 - 1, k0, ex);
|
||||
fxx[p]=ZEO; fyy[p]=ZEO; fzz[p]=ZEO;
|
||||
fxy[p]=ZEO; fxz[p]=ZEO; fyz[p]=ZEO;
|
||||
}
|
||||
/* 高边界：i0=ex1-1 */
|
||||
for (int k0 = 0; k0 < ex3 - 1; ++k0)
|
||||
for (int j0 = 0; j0 < ex2 - 1; ++j0) {
|
||||
const size_t p = idx_ex(ex1 - 1, j0, k0, ex);
|
||||
fxx[p]=ZEO; fyy[p]=ZEO; fzz[p]=ZEO;
|
||||
fxy[p]=ZEO; fxz[p]=ZEO; fyz[p]=ZEO;
|
||||
}
|
||||
|
||||
/* 低边界：当二阶模板也不可用时，对应 i0/j0/k0=0 面 */
|
||||
if (kminF == 1) {
|
||||
for (int j0 = 0; j0 < ex2; ++j0)
|
||||
for (int i0 = 0; i0 < ex1; ++i0) {
|
||||
const size_t p = idx_ex(i0, j0, 0, ex);
|
||||
fxx[p]=ZEO; fyy[p]=ZEO; fzz[p]=ZEO;
|
||||
fxy[p]=ZEO; fxz[p]=ZEO; fyz[p]=ZEO;
|
||||
}
|
||||
}
|
||||
if (jminF == 1) {
|
||||
for (int k0 = 0; k0 < ex3; ++k0)
|
||||
for (int i0 = 0; i0 < ex1; ++i0) {
|
||||
const size_t p = idx_ex(i0, 0, k0, ex);
|
||||
fxx[p]=ZEO; fyy[p]=ZEO; fzz[p]=ZEO;
|
||||
fxy[p]=ZEO; fxz[p]=ZEO; fyz[p]=ZEO;
|
||||
}
|
||||
}
|
||||
if (iminF == 1) {
|
||||
for (int k0 = 0; k0 < ex3; ++k0)
|
||||
for (int j0 = 0; j0 < ex2; ++j0) {
|
||||
const size_t p = idx_ex(0, j0, k0, ex);
|
||||
fxx[p]=ZEO; fyy[p]=ZEO; fzz[p]=ZEO;
|
||||
fxy[p]=ZEO; fxz[p]=ZEO; fyz[p]=ZEO;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* 两段式：
|
||||
* 1) 二阶可用区域先计算二阶模板
|
||||
* 2) 高阶可用区域再覆盖四阶模板
|
||||
*/
|
||||
const int i2_lo = (iminF > 0) ? iminF : 0;
|
||||
const int j2_lo = (jminF > 0) ? jminF : 0;
|
||||
const int k2_lo = (kminF > 0) ? kminF : 0;
|
||||
const int i2_hi = ex1 - 2;
|
||||
const int j2_hi = ex2 - 2;
|
||||
const int k2_hi = ex3 - 2;
|
||||
|
||||
const int i4_lo = (iminF + 1 > 0) ? (iminF + 1) : 0;
|
||||
const int j4_lo = (jminF + 1 > 0) ? (jminF + 1) : 0;
|
||||
const int k4_lo = (kminF + 1 > 0) ? (kminF + 1) : 0;
|
||||
const int i4_hi = ex1 - 3;
|
||||
const int j4_hi = ex2 - 3;
|
||||
const int k4_hi = ex3 - 3;
|
||||
|
||||
/*
|
||||
* Strategy A:
|
||||
* Avoid redundant work in overlap of 2nd/4th-order regions.
|
||||
* Only compute 2nd-order on shell points that are NOT overwritten by
|
||||
* the 4th-order pass.
|
||||
*/
|
||||
const int has4 = (i4_lo <= i4_hi && j4_lo <= j4_hi && k4_lo <= k4_hi);
|
||||
|
||||
if (i2_lo <= i2_hi && j2_lo <= j2_hi && k2_lo <= k2_hi) {
|
||||
for (int k0 = k2_lo; k0 <= k2_hi; ++k0) {
|
||||
const int kF = k0 + 1;
|
||||
for (int j0 = j2_lo; j0 <= j2_hi; ++j0) {
|
||||
const int jF = j0 + 1;
|
||||
for (int i0 = i2_lo; i0 <= i2_hi; ++i0) {
|
||||
if (has4 &&
|
||||
i0 >= i4_lo && i0 <= i4_hi &&
|
||||
j0 >= j4_lo && j0 <= j4_hi &&
|
||||
k0 >= k4_lo && k0 <= k4_hi) {
|
||||
continue;
|
||||
}
|
||||
const int iF = i0 + 1;
|
||||
const size_t p = idx_ex(i0, j0, k0, ex);
|
||||
|
||||
fxx[p] = Sdxdx * (
|
||||
fh[idx_fh_F_ord2(iF - 1, jF, kF, ex)] -
|
||||
TWO * fh[idx_fh_F_ord2(iF, jF, kF, ex)] +
|
||||
fh[idx_fh_F_ord2(iF + 1, jF, kF, ex)]
|
||||
);
|
||||
|
||||
fyy[p] = Sdydy * (
|
||||
fh[idx_fh_F_ord2(iF, jF - 1, kF, ex)] -
|
||||
TWO * fh[idx_fh_F_ord2(iF, jF, kF, ex)] +
|
||||
fh[idx_fh_F_ord2(iF, jF + 1, kF, ex)]
|
||||
);
|
||||
|
||||
fzz[p] = Sdzdz * (
|
||||
fh[idx_fh_F_ord2(iF, jF, kF - 1, ex)] -
|
||||
TWO * fh[idx_fh_F_ord2(iF, jF, kF, ex)] +
|
||||
fh[idx_fh_F_ord2(iF, jF, kF + 1, ex)]
|
||||
);
|
||||
|
||||
fxy[p] = Sdxdy * (
|
||||
fh[idx_fh_F_ord2(iF - 1, jF - 1, kF, ex)] -
|
||||
fh[idx_fh_F_ord2(iF + 1, jF - 1, kF, ex)] -
|
||||
fh[idx_fh_F_ord2(iF - 1, jF + 1, kF, ex)] +
|
||||
fh[idx_fh_F_ord2(iF + 1, jF + 1, kF, ex)]
|
||||
);
|
||||
|
||||
fxz[p] = Sdxdz * (
|
||||
fh[idx_fh_F_ord2(iF - 1, jF, kF - 1, ex)] -
|
||||
fh[idx_fh_F_ord2(iF + 1, jF, kF - 1, ex)] -
|
||||
fh[idx_fh_F_ord2(iF - 1, jF, kF + 1, ex)] +
|
||||
fh[idx_fh_F_ord2(iF + 1, jF, kF + 1, ex)]
|
||||
);
|
||||
|
||||
fyz[p] = Sdydz * (
|
||||
fh[idx_fh_F_ord2(iF, jF - 1, kF - 1, ex)] -
|
||||
fh[idx_fh_F_ord2(iF, jF + 1, kF - 1, ex)] -
|
||||
fh[idx_fh_F_ord2(iF, jF - 1, kF + 1, ex)] +
|
||||
fh[idx_fh_F_ord2(iF, jF + 1, kF + 1, ex)]
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (has4) {
|
||||
for (int k0 = k4_lo; k0 <= k4_hi; ++k0) {
|
||||
const int kF = k0 + 1;
|
||||
for (int j0 = j4_lo; j0 <= j4_hi; ++j0) {
|
||||
const int jF = j0 + 1;
|
||||
for (int i0 = i4_lo; i0 <= i4_hi; ++i0) {
|
||||
const int iF = i0 + 1;
|
||||
const size_t p = idx_ex(i0, j0, k0, ex);
|
||||
|
||||
fxx[p] = Fdxdx * (
|
||||
-fh[idx_fh_F_ord2(iF - 2, jF, kF, ex)] +
|
||||
F16 * fh[idx_fh_F_ord2(iF - 1, jF, kF, ex)] -
|
||||
F30 * fh[idx_fh_F_ord2(iF, jF, kF, ex)] -
|
||||
fh[idx_fh_F_ord2(iF + 2, jF, kF, ex)] +
|
||||
F16 * fh[idx_fh_F_ord2(iF + 1, jF, kF, ex)]
|
||||
);
|
||||
|
||||
fyy[p] = Fdydy * (
|
||||
-fh[idx_fh_F_ord2(iF, jF - 2, kF, ex)] +
|
||||
F16 * fh[idx_fh_F_ord2(iF, jF - 1, kF, ex)] -
|
||||
F30 * fh[idx_fh_F_ord2(iF, jF, kF, ex)] -
|
||||
fh[idx_fh_F_ord2(iF, jF + 2, kF, ex)] +
|
||||
F16 * fh[idx_fh_F_ord2(iF, jF + 1, kF, ex)]
|
||||
);
|
||||
|
||||
fzz[p] = Fdzdz * (
|
||||
-fh[idx_fh_F_ord2(iF, jF, kF - 2, ex)] +
|
||||
F16 * fh[idx_fh_F_ord2(iF, jF, kF - 1, ex)] -
|
||||
F30 * fh[idx_fh_F_ord2(iF, jF, kF, ex)] -
|
||||
fh[idx_fh_F_ord2(iF, jF, kF + 2, ex)] +
|
||||
F16 * fh[idx_fh_F_ord2(iF, jF, kF + 1, ex)]
|
||||
);
|
||||
|
||||
{
|
||||
const double t_jm2 =
|
||||
( fh[idx_fh_F_ord2(iF - 2, jF - 2, kF, ex)]
|
||||
-F8*fh[idx_fh_F_ord2(iF - 1, jF - 2, kF, ex)]
|
||||
+F8*fh[idx_fh_F_ord2(iF + 1, jF - 2, kF, ex)]
|
||||
- fh[idx_fh_F_ord2(iF + 2, jF - 2, kF, ex)] );
|
||||
|
||||
const double t_jm1 =
|
||||
( fh[idx_fh_F_ord2(iF - 2, jF - 1, kF, ex)]
|
||||
-F8*fh[idx_fh_F_ord2(iF - 1, jF - 1, kF, ex)]
|
||||
+F8*fh[idx_fh_F_ord2(iF + 1, jF - 1, kF, ex)]
|
||||
- fh[idx_fh_F_ord2(iF + 2, jF - 1, kF, ex)] );
|
||||
|
||||
const double t_jp1 =
|
||||
( fh[idx_fh_F_ord2(iF - 2, jF + 1, kF, ex)]
|
||||
-F8*fh[idx_fh_F_ord2(iF - 1, jF + 1, kF, ex)]
|
||||
+F8*fh[idx_fh_F_ord2(iF + 1, jF + 1, kF, ex)]
|
||||
- fh[idx_fh_F_ord2(iF + 2, jF + 1, kF, ex)] );
|
||||
|
||||
const double t_jp2 =
|
||||
( fh[idx_fh_F_ord2(iF - 2, jF + 2, kF, ex)]
|
||||
-F8*fh[idx_fh_F_ord2(iF - 1, jF + 2, kF, ex)]
|
||||
+F8*fh[idx_fh_F_ord2(iF + 1, jF + 2, kF, ex)]
|
||||
- fh[idx_fh_F_ord2(iF + 2, jF + 2, kF, ex)] );
|
||||
|
||||
fxy[p] = Fdxdy * ( t_jm2 - F8 * t_jm1 + F8 * t_jp1 - t_jp2 );
|
||||
}
|
||||
|
||||
{
|
||||
const double t_km2 =
|
||||
( fh[idx_fh_F_ord2(iF - 2, jF, kF - 2, ex)]
|
||||
-F8*fh[idx_fh_F_ord2(iF - 1, jF, kF - 2, ex)]
|
||||
+F8*fh[idx_fh_F_ord2(iF + 1, jF, kF - 2, ex)]
|
||||
- fh[idx_fh_F_ord2(iF + 2, jF, kF - 2, ex)] );
|
||||
|
||||
const double t_km1 =
|
||||
( fh[idx_fh_F_ord2(iF - 2, jF, kF - 1, ex)]
|
||||
-F8*fh[idx_fh_F_ord2(iF - 1, jF, kF - 1, ex)]
|
||||
+F8*fh[idx_fh_F_ord2(iF + 1, jF, kF - 1, ex)]
|
||||
- fh[idx_fh_F_ord2(iF + 2, jF, kF - 1, ex)] );
|
||||
|
||||
const double t_kp1 =
|
||||
( fh[idx_fh_F_ord2(iF - 2, jF, kF + 1, ex)]
|
||||
-F8*fh[idx_fh_F_ord2(iF - 1, jF, kF + 1, ex)]
|
||||
+F8*fh[idx_fh_F_ord2(iF + 1, jF, kF + 1, ex)]
|
||||
- fh[idx_fh_F_ord2(iF + 2, jF, kF + 1, ex)] );
|
||||
|
||||
const double t_kp2 =
|
||||
( fh[idx_fh_F_ord2(iF - 2, jF, kF + 2, ex)]
|
||||
-F8*fh[idx_fh_F_ord2(iF - 1, jF, kF + 2, ex)]
|
||||
+F8*fh[idx_fh_F_ord2(iF + 1, jF, kF + 2, ex)]
|
||||
- fh[idx_fh_F_ord2(iF + 2, jF, kF + 2, ex)] );
|
||||
|
||||
fxz[p] = Fdxdz * ( t_km2 - F8 * t_km1 + F8 * t_kp1 - t_kp2 );
|
||||
}
|
||||
|
||||
{
|
||||
const double t_km2 =
|
||||
( fh[idx_fh_F_ord2(iF, jF - 2, kF - 2, ex)]
|
||||
-F8*fh[idx_fh_F_ord2(iF, jF - 1, kF - 2, ex)]
|
||||
+F8*fh[idx_fh_F_ord2(iF, jF + 1, kF - 2, ex)]
|
||||
- fh[idx_fh_F_ord2(iF, jF + 2, kF - 2, ex)] );
|
||||
|
||||
const double t_km1 =
|
||||
( fh[idx_fh_F_ord2(iF, jF - 2, kF - 1, ex)]
|
||||
-F8*fh[idx_fh_F_ord2(iF, jF - 1, kF - 1, ex)]
|
||||
+F8*fh[idx_fh_F_ord2(iF, jF + 1, kF - 1, ex)]
|
||||
- fh[idx_fh_F_ord2(iF, jF + 2, kF - 1, ex)] );
|
||||
|
||||
const double t_kp1 =
|
||||
( fh[idx_fh_F_ord2(iF, jF - 2, kF + 1, ex)]
|
||||
-F8*fh[idx_fh_F_ord2(iF, jF - 1, kF + 1, ex)]
|
||||
+F8*fh[idx_fh_F_ord2(iF, jF + 1, kF + 1, ex)]
|
||||
- fh[idx_fh_F_ord2(iF, jF + 2, kF + 1, ex)] );
|
||||
|
||||
const double t_kp2 =
|
||||
( fh[idx_fh_F_ord2(iF, jF - 2, kF + 2, ex)]
|
||||
-F8*fh[idx_fh_F_ord2(iF, jF - 1, kF + 2, ex)]
|
||||
+F8*fh[idx_fh_F_ord2(iF, jF + 1, kF + 2, ex)]
|
||||
- fh[idx_fh_F_ord2(iF, jF + 2, kF + 2, ex)] );
|
||||
|
||||
fyz[p] = Fdydz * ( t_km2 - F8 * t_km1 + F8 * t_kp1 - t_kp2 );
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// free(fh);
|
||||
}
|
||||
@@ -1,167 +0,0 @@
|
||||
#include "tool.h"
|
||||
|
||||
/*
|
||||
* C 版 fderivs
|
||||
*
|
||||
* Fortran:
|
||||
* subroutine fderivs(ex,f,fx,fy,fz,X,Y,Z,SYM1,SYM2,SYM3,symmetry,onoff)
|
||||
*
|
||||
* 约定：
|
||||
* f, fx, fy, fz: ex1*ex2*ex3，按 idx_ex 布局
|
||||
* X: ex1, Y: ex2, Z: ex3
|
||||
*/
|
||||
void fderivs(const int ex[3],
|
||||
const double *f,
|
||||
double *fx, double *fy, double *fz,
|
||||
const double *X, const double *Y, const double *Z,
|
||||
double SYM1, double SYM2, double SYM3,
|
||||
int Symmetry, int onoff)
|
||||
{
|
||||
(void)onoff; // Fortran 里没用到
|
||||
|
||||
const double ZEO = 0.0, ONE = 1.0;
|
||||
const double TWO = 2.0, EIT = 8.0;
|
||||
const double F12 = 12.0;
|
||||
|
||||
const int NO_SYMM = 0, EQ_SYMM = 1; // OCTANT=2 在本子程序里不直接用
|
||||
|
||||
const int ex1 = ex[0], ex2 = ex[1], ex3 = ex[2];
|
||||
|
||||
// dX = X(2)-X(1) -> C: X[1]-X[0]
|
||||
const double dX = X[1] - X[0];
|
||||
const double dY = Y[1] - Y[0];
|
||||
const double dZ = Z[1] - Z[0];
|
||||
|
||||
// Fortran 1-based bounds
|
||||
const int imaxF = ex1;
|
||||
const int jmaxF = ex2;
|
||||
const int kmaxF = ex3;
|
||||
|
||||
int iminF = 1, jminF = 1, kminF = 1;
|
||||
if (Symmetry > NO_SYMM && fabs(Z[0]) < dZ) kminF = -1;
|
||||
if (Symmetry > EQ_SYMM && fabs(X[0]) < dX) iminF = -1;
|
||||
if (Symmetry > EQ_SYMM && fabs(Y[0]) < dY) jminF = -1;
|
||||
|
||||
// SoA(1:3) = SYM1,SYM2,SYM3
|
||||
const double SoA[3] = { SYM1, SYM2, SYM3 };
|
||||
|
||||
// fh: (ex1+2)*(ex2+2)*(ex3+2) because ord=2
|
||||
const size_t nx = (size_t)ex1 + 2;
|
||||
const size_t ny = (size_t)ex2 + 2;
|
||||
const size_t nz = (size_t)ex3 + 2;
|
||||
const size_t fh_size = nx * ny * nz;
|
||||
static double *fh = NULL;
|
||||
static size_t cap = 0;
|
||||
|
||||
if (fh_size > cap) {
|
||||
free(fh);
|
||||
fh = (double*)aligned_alloc(64, fh_size * sizeof(double));
|
||||
cap = fh_size;
|
||||
}
|
||||
// double *fh = (double*)malloc(fh_size * sizeof(double));
|
||||
if (!fh) return;
|
||||
|
||||
// call symmetry_bd(2,ex,f,fh,SoA)
|
||||
symmetry_bd(2, ex, f, fh, SoA);
|
||||
|
||||
const double d12dx = ONE / F12 / dX;
|
||||
const double d12dy = ONE / F12 / dY;
|
||||
const double d12dz = ONE / F12 / dZ;
|
||||
|
||||
const double d2dx = ONE / TWO / dX;
|
||||
const double d2dy = ONE / TWO / dY;
|
||||
const double d2dz = ONE / TWO / dZ;
|
||||
|
||||
// fx = fy = fz = 0
|
||||
const size_t all = (size_t)ex1 * (size_t)ex2 * (size_t)ex3;
|
||||
for (size_t p = 0; p < all; ++p) {
|
||||
fx[p] = ZEO;
|
||||
fy[p] = ZEO;
|
||||
fz[p] = ZEO;
|
||||
}
|
||||
|
||||
/*
|
||||
* 两段式：
|
||||
* 1) 先在二阶可用区域计算二阶模板
|
||||
* 2) 再在高阶可用区域覆盖为四阶模板
|
||||
*
|
||||
* 与原 if/elseif 逻辑等价，但减少逐点分支判断。
|
||||
*/
|
||||
const int i2_lo = (iminF > 0) ? iminF : 0;
|
||||
const int j2_lo = (jminF > 0) ? jminF : 0;
|
||||
const int k2_lo = (kminF > 0) ? kminF : 0;
|
||||
const int i2_hi = ex1 - 2;
|
||||
const int j2_hi = ex2 - 2;
|
||||
const int k2_hi = ex3 - 2;
|
||||
|
||||
const int i4_lo = (iminF + 1 > 0) ? (iminF + 1) : 0;
|
||||
const int j4_lo = (jminF + 1 > 0) ? (jminF + 1) : 0;
|
||||
const int k4_lo = (kminF + 1 > 0) ? (kminF + 1) : 0;
|
||||
const int i4_hi = ex1 - 3;
|
||||
const int j4_hi = ex2 - 3;
|
||||
const int k4_hi = ex3 - 3;
|
||||
|
||||
if (i2_lo <= i2_hi && j2_lo <= j2_hi && k2_lo <= k2_hi) {
|
||||
for (int k0 = k2_lo; k0 <= k2_hi; ++k0) {
|
||||
const int kF = k0 + 1;
|
||||
for (int j0 = j2_lo; j0 <= j2_hi; ++j0) {
|
||||
const int jF = j0 + 1;
|
||||
for (int i0 = i2_lo; i0 <= i2_hi; ++i0) {
|
||||
const int iF = i0 + 1;
|
||||
const size_t p = idx_ex(i0, j0, k0, ex);
|
||||
|
||||
fx[p] = d2dx * (
|
||||
-fh[idx_fh_F_ord2(iF - 1, jF, kF, ex)] +
|
||||
fh[idx_fh_F_ord2(iF + 1, jF, kF, ex)]
|
||||
);
|
||||
|
||||
fy[p] = d2dy * (
|
||||
-fh[idx_fh_F_ord2(iF, jF - 1, kF, ex)] +
|
||||
fh[idx_fh_F_ord2(iF, jF + 1, kF, ex)]
|
||||
);
|
||||
|
||||
fz[p] = d2dz * (
|
||||
-fh[idx_fh_F_ord2(iF, jF, kF - 1, ex)] +
|
||||
fh[idx_fh_F_ord2(iF, jF, kF + 1, ex)]
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (i4_lo <= i4_hi && j4_lo <= j4_hi && k4_lo <= k4_hi) {
|
||||
for (int k0 = k4_lo; k0 <= k4_hi; ++k0) {
|
||||
const int kF = k0 + 1;
|
||||
for (int j0 = j4_lo; j0 <= j4_hi; ++j0) {
|
||||
const int jF = j0 + 1;
|
||||
for (int i0 = i4_lo; i0 <= i4_hi; ++i0) {
|
||||
const int iF = i0 + 1;
|
||||
const size_t p = idx_ex(i0, j0, k0, ex);
|
||||
|
||||
fx[p] = d12dx * (
|
||||
fh[idx_fh_F_ord2(iF - 2, jF, kF, ex)] -
|
||||
EIT * fh[idx_fh_F_ord2(iF - 1, jF, kF, ex)] +
|
||||
EIT * fh[idx_fh_F_ord2(iF + 1, jF, kF, ex)] -
|
||||
fh[idx_fh_F_ord2(iF + 2, jF, kF, ex)]
|
||||
);
|
||||
|
||||
fy[p] = d12dy * (
|
||||
fh[idx_fh_F_ord2(iF, jF - 2, kF, ex)] -
|
||||
EIT * fh[idx_fh_F_ord2(iF, jF - 1, kF, ex)] +
|
||||
EIT * fh[idx_fh_F_ord2(iF, jF + 1, kF, ex)] -
|
||||
fh[idx_fh_F_ord2(iF, jF + 2, kF, ex)]
|
||||
);
|
||||
|
||||
fz[p] = d12dz * (
|
||||
fh[idx_fh_F_ord2(iF, jF, kF - 2, ex)] -
|
||||
EIT * fh[idx_fh_F_ord2(iF, jF, kF - 1, ex)] +
|
||||
EIT * fh[idx_fh_F_ord2(iF, jF, kF + 1, ex)] -
|
||||
fh[idx_fh_F_ord2(iF, jF, kF + 2, ex)]
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// free(fh);
|
||||
}
|
||||
@@ -1,117 +0,0 @@
|
||||
#include "tool.h"
|
||||
|
||||
/*
|
||||
* C 版 kodis
|
||||
*
|
||||
* Fortran signature:
|
||||
* subroutine kodis(ex,X,Y,Z,f,f_rhs,SoA,Symmetry,eps)
|
||||
*
|
||||
* 约定：
|
||||
* X: ex1, Y: ex2, Z: ex3
|
||||
* f, f_rhs: ex1*ex2*ex3 按 idx_ex 布局
|
||||
* SoA[3]
|
||||
* eps: double
|
||||
*/
|
||||
void kodis(const int ex[3],
|
||||
const double *X, const double *Y, const double *Z,
|
||||
const double *f, double *f_rhs,
|
||||
const double SoA[3],
|
||||
int Symmetry, double eps)
|
||||
{
|
||||
const double ONE = 1.0, SIX = 6.0, FIT = 15.0, TWT = 20.0;
|
||||
const double cof = 64.0; // 2^6
|
||||
const int NO_SYMM = 0, OCTANT = 2;
|
||||
|
||||
const int ex1 = ex[0], ex2 = ex[1], ex3 = ex[2];
|
||||
|
||||
// Fortran: dX = X(2)-X(1) -> C: X[1]-X[0]
|
||||
const double dX = X[1] - X[0];
|
||||
const double dY = Y[1] - Y[0];
|
||||
const double dZ = Z[1] - Z[0];
|
||||
(void)ONE; // ONE 在原 Fortran 里只是参数，这里不一定用得上
|
||||
|
||||
// Fortran: imax=ex(1) 等是 1-based 上界
|
||||
const int imaxF = ex1;
|
||||
const int jmaxF = ex2;
|
||||
const int kmaxF = ex3;
|
||||
|
||||
// Fortran: imin=jmin=kmin=1，某些对称情况变 -2
|
||||
int iminF = 1, jminF = 1, kminF = 1;
|
||||
|
||||
if (Symmetry > NO_SYMM && fabs(Z[0]) < dZ) kminF = -2;
|
||||
if (Symmetry == OCTANT && fabs(X[0]) < dX) iminF = -2;
|
||||
if (Symmetry == OCTANT && fabs(Y[0]) < dY) jminF = -2;
|
||||
|
||||
// 分配 fh：大小 (ex1+3)*(ex2+3)*(ex3+3)，对应 ord=3
|
||||
const size_t nx = (size_t)ex1 + 3;
|
||||
const size_t ny = (size_t)ex2 + 3;
|
||||
const size_t nz = (size_t)ex3 + 3;
|
||||
const size_t fh_size = nx * ny * nz;
|
||||
|
||||
double *fh = (double*)malloc(fh_size * sizeof(double));
|
||||
if (!fh) return;
|
||||
|
||||
// Fortran: call symmetry_bd(3,ex,f,fh,SoA)
|
||||
symmetry_bd(3, ex, f, fh, SoA);
|
||||
|
||||
/*
|
||||
* Fortran loops:
|
||||
* do k=1,ex3
|
||||
* do j=1,ex2
|
||||
* do i=1,ex1
|
||||
*
|
||||
* C: k0=0..ex3-1, j0=0..ex2-1, i0=0..ex1-1
|
||||
* 并定义 Fortran index: iF=i0+1, ...
|
||||
*/
|
||||
// 收紧循环范围：只遍历满足 iF±3/jF±3/kF±3 条件的内部点
|
||||
// iF-3 >= iminF => iF >= iminF+3 => i0 >= iminF+2 (因为 iF=i0+1)
|
||||
// iF+3 <= imaxF => iF <= imaxF-3 => i0 <= imaxF-4
|
||||
const int i0_lo = (iminF + 2 > 0) ? iminF + 2 : 0;
|
||||
const int j0_lo = (jminF + 2 > 0) ? jminF + 2 : 0;
|
||||
const int k0_lo = (kminF + 2 > 0) ? kminF + 2 : 0;
|
||||
const int i0_hi = imaxF - 4; // inclusive
|
||||
const int j0_hi = jmaxF - 4;
|
||||
const int k0_hi = kmaxF - 4;
|
||||
|
||||
if (i0_lo > i0_hi || j0_lo > j0_hi || k0_lo > k0_hi) {
|
||||
free(fh);
|
||||
return;
|
||||
}
|
||||
|
||||
for (int k0 = k0_lo; k0 <= k0_hi; ++k0) {
|
||||
const int kF = k0 + 1;
|
||||
for (int j0 = j0_lo; j0 <= j0_hi; ++j0) {
|
||||
const int jF = j0 + 1;
|
||||
for (int i0 = i0_lo; i0 <= i0_hi; ++i0) {
|
||||
const int iF = i0 + 1;
|
||||
|
||||
const size_t p = idx_ex(i0, j0, k0, ex);
|
||||
|
||||
// 三个方向各一份同型的 7 点组合（实际上是对称的 6th-order dissipation/filter 核）
|
||||
const double Dx_term =
|
||||
( (fh[idx_fh_F(iF - 3, jF, kF, ex)] + fh[idx_fh_F(iF + 3, jF, kF, ex)]) -
|
||||
SIX * (fh[idx_fh_F(iF - 2, jF, kF, ex)] + fh[idx_fh_F(iF + 2, jF, kF, ex)]) +
|
||||
FIT * (fh[idx_fh_F(iF - 1, jF, kF, ex)] + fh[idx_fh_F(iF + 1, jF, kF, ex)]) -
|
||||
TWT * fh[idx_fh_F(iF , jF, kF, ex)] ) / dX;
|
||||
|
||||
const double Dy_term =
|
||||
( (fh[idx_fh_F(iF, jF - 3, kF, ex)] + fh[idx_fh_F(iF, jF + 3, kF, ex)]) -
|
||||
SIX * (fh[idx_fh_F(iF, jF - 2, kF, ex)] + fh[idx_fh_F(iF, jF + 2, kF, ex)]) +
|
||||
FIT * (fh[idx_fh_F(iF, jF - 1, kF, ex)] + fh[idx_fh_F(iF, jF + 1, kF, ex)]) -
|
||||
TWT * fh[idx_fh_F(iF, jF , kF, ex)] ) / dY;
|
||||
|
||||
const double Dz_term =
|
||||
( (fh[idx_fh_F(iF, jF, kF - 3, ex)] + fh[idx_fh_F(iF, jF, kF + 3, ex)]) -
|
||||
SIX * (fh[idx_fh_F(iF, jF, kF - 2, ex)] + fh[idx_fh_F(iF, jF, kF + 2, ex)]) +
|
||||
FIT * (fh[idx_fh_F(iF, jF, kF - 1, ex)] + fh[idx_fh_F(iF, jF, kF + 1, ex)]) -
|
||||
TWT * fh[idx_fh_F(iF, jF, kF , ex)] ) / dZ;
|
||||
|
||||
// Fortran:
|
||||
// f_rhs(i,j,k) = f_rhs(i,j,k) + eps/cof*(Dx_term + Dy_term + Dz_term)
|
||||
f_rhs[p] += (eps / cof) * (Dx_term + Dy_term + Dz_term);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
free(fh);
|
||||
}
|
||||
@@ -7,178 +7,12 @@
|
||||
#include <string>
|
||||
#include <cmath>
|
||||
#include <new>
|
||||
#include <vector>
|
||||
using namespace std;
|
||||
|
||||
#include "misc.h"
|
||||
#include "MPatch.h"
|
||||
#include "Parallel.h"
|
||||
#include "fmisc.h"
|
||||
#ifdef INTERP_LB_PROFILE
|
||||
#include "interp_lb_profile.h"
|
||||
#endif
|
||||
|
||||
namespace
|
||||
{
|
||||
struct InterpBlockView
|
||||
{
|
||||
Block *bp;
|
||||
double llb[dim];
|
||||
double uub[dim];
|
||||
};
|
||||
|
||||
struct BlockBinIndex
|
||||
{
|
||||
int bins[dim];
|
||||
double lo[dim];
|
||||
double inv[dim];
|
||||
vector<InterpBlockView> views;
|
||||
vector<vector<int>> bin_to_blocks;
|
||||
bool valid;
|
||||
|
||||
BlockBinIndex() : valid(false)
|
||||
{
|
||||
for (int i = 0; i < dim; i++)
|
||||
{
|
||||
bins[i] = 1;
|
||||
lo[i] = 0.0;
|
||||
inv[i] = 0.0;
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
inline int clamp_int(int v, int lo, int hi)
|
||||
{
|
||||
return (v < lo) ? lo : ((v > hi) ? hi : v);
|
||||
}
|
||||
|
||||
inline int coord_to_bin(double x, double lo, double inv, int nb)
|
||||
{
|
||||
if (nb <= 1 || inv <= 0.0)
|
||||
return 0;
|
||||
int b = int(floor((x - lo) * inv));
|
||||
return clamp_int(b, 0, nb - 1);
|
||||
}
|
||||
|
||||
inline int bin_loc(const BlockBinIndex &index, int b0, int b1, int b2)
|
||||
{
|
||||
return b0 + index.bins[0] * (b1 + index.bins[1] * b2);
|
||||
}
|
||||
|
||||
inline bool point_in_block_view(const InterpBlockView &view, const double *pox, const double *DH)
|
||||
{
|
||||
for (int i = 0; i < dim; i++)
|
||||
{
|
||||
if (pox[i] - view.llb[i] < -DH[i] / 2 || pox[i] - view.uub[i] > DH[i] / 2)
|
||||
return false;
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
void build_block_bin_index(Patch *patch, const double *DH, BlockBinIndex &index)
|
||||
{
|
||||
index = BlockBinIndex();
|
||||
|
||||
MyList<Block> *Bp = patch->blb;
|
||||
while (Bp)
|
||||
{
|
||||
Block *BP = Bp->data;
|
||||
InterpBlockView view;
|
||||
view.bp = BP;
|
||||
for (int i = 0; i < dim; i++)
|
||||
{
|
||||
#ifdef Vertex
|
||||
#ifdef Cell
|
||||
#error Both Cell and Vertex are defined
|
||||
#endif
|
||||
view.llb[i] = (feq(BP->bbox[i], patch->bbox[i], DH[i] / 2)) ? BP->bbox[i] + patch->lli[i] * DH[i] : BP->bbox[i] + (ghost_width - 0.5) * DH[i];
|
||||
view.uub[i] = (feq(BP->bbox[dim + i], patch->bbox[dim + i], DH[i] / 2)) ? BP->bbox[dim + i] - patch->uui[i] * DH[i] : BP->bbox[dim + i] - (ghost_width - 0.5) * DH[i];
|
||||
#else
|
||||
#ifdef Cell
|
||||
view.llb[i] = (feq(BP->bbox[i], patch->bbox[i], DH[i] / 2)) ? BP->bbox[i] + patch->lli[i] * DH[i] : BP->bbox[i] + ghost_width * DH[i];
|
||||
view.uub[i] = (feq(BP->bbox[dim + i], patch->bbox[dim + i], DH[i] / 2)) ? BP->bbox[dim + i] - patch->uui[i] * DH[i] : BP->bbox[dim + i] - ghost_width * DH[i];
|
||||
#else
|
||||
#error Not define Vertex nor Cell
|
||||
#endif
|
||||
#endif
|
||||
}
|
||||
index.views.push_back(view);
|
||||
if (Bp == patch->ble)
|
||||
break;
|
||||
Bp = Bp->next;
|
||||
}
|
||||
|
||||
const int nblocks = int(index.views.size());
|
||||
if (nblocks <= 0)
|
||||
return;
|
||||
|
||||
int bins_1d = int(ceil(pow(double(nblocks), 1.0 / 3.0)));
|
||||
bins_1d = clamp_int(bins_1d, 1, 32);
|
||||
for (int i = 0; i < dim; i++)
|
||||
{
|
||||
index.bins[i] = bins_1d;
|
||||
index.lo[i] = patch->bbox[i] + patch->lli[i] * DH[i];
|
||||
const double hi = patch->bbox[dim + i] - patch->uui[i] * DH[i];
|
||||
if (hi > index.lo[i] && bins_1d > 1)
|
||||
index.inv[i] = bins_1d / (hi - index.lo[i]);
|
||||
else
|
||||
index.inv[i] = 0.0;
|
||||
}
|
||||
|
||||
index.bin_to_blocks.resize(index.bins[0] * index.bins[1] * index.bins[2]);
|
||||
|
||||
for (int bi = 0; bi < nblocks; bi++)
|
||||
{
|
||||
const InterpBlockView &view = index.views[bi];
|
||||
int bmin[dim], bmax[dim];
|
||||
for (int d = 0; d < dim; d++)
|
||||
{
|
||||
const double low = view.llb[d] - DH[d] / 2;
|
||||
const double up = view.uub[d] + DH[d] / 2;
|
||||
bmin[d] = coord_to_bin(low, index.lo[d], index.inv[d], index.bins[d]);
|
||||
bmax[d] = coord_to_bin(up, index.lo[d], index.inv[d], index.bins[d]);
|
||||
if (bmax[d] < bmin[d])
|
||||
{
|
||||
int t = bmin[d];
|
||||
bmin[d] = bmax[d];
|
||||
bmax[d] = t;
|
||||
}
|
||||
}
|
||||
|
||||
for (int bz = bmin[2]; bz <= bmax[2]; bz++)
|
||||
for (int by = bmin[1]; by <= bmax[1]; by++)
|
||||
for (int bx = bmin[0]; bx <= bmax[0]; bx++)
|
||||
index.bin_to_blocks[bin_loc(index, bx, by, bz)].push_back(bi);
|
||||
}
|
||||
|
||||
index.valid = true;
|
||||
}
|
||||
|
||||
int find_block_index_for_point(const BlockBinIndex &index, const double *pox, const double *DH)
|
||||
{
|
||||
if (!index.valid)
|
||||
return -1;
|
||||
|
||||
const int bx = coord_to_bin(pox[0], index.lo[0], index.inv[0], index.bins[0]);
|
||||
const int by = coord_to_bin(pox[1], index.lo[1], index.inv[1], index.bins[1]);
|
||||
const int bz = coord_to_bin(pox[2], index.lo[2], index.inv[2], index.bins[2]);
|
||||
const vector<int> &cand = index.bin_to_blocks[bin_loc(index, bx, by, bz)];
|
||||
|
||||
for (size_t ci = 0; ci < cand.size(); ci++)
|
||||
{
|
||||
const int bi = cand[ci];
|
||||
if (point_in_block_view(index.views[bi], pox, DH))
|
||||
return bi;
|
||||
}
|
||||
|
||||
// Fallback to full scan for numerical edge cases around bin boundaries.
|
||||
for (size_t bi = 0; bi < index.views.size(); bi++)
|
||||
if (point_in_block_view(index.views[bi], pox, DH))
|
||||
return int(bi);
|
||||
|
||||
return -1;
|
||||
}
|
||||
} // namespace
|
||||
|
||||
Patch::Patch(int DIM, int *shapei, double *bboxi, int levi, bool buflog, int Symmetry) : lev(levi)
|
||||
{
|
||||
@@ -507,9 +341,8 @@ void Patch::Interp_Points(MyList<var> *VarList,
|
||||
double *Shellf, int Symmetry)
|
||||
{
|
||||
// NOTE: we do not Synchnize variables here, make sure of that before calling this routine
|
||||
int myrank, nprocs;
|
||||
int myrank;
|
||||
MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
|
||||
MPI_Comm_size(MPI_COMM_WORLD, &nprocs);
|
||||
|
||||
int ordn = 2 * ghost_width;
|
||||
MyList<var> *varl;
|
||||
@@ -521,20 +354,24 @@ void Patch::Interp_Points(MyList<var> *VarList,
|
||||
varl = varl->next;
|
||||
}
|
||||
|
||||
memset(Shellf, 0, sizeof(double) * NN * num_var);
|
||||
double *shellf;
|
||||
shellf = new double[NN * num_var];
|
||||
memset(shellf, 0, sizeof(double) * NN * num_var);
|
||||
|
||||
// owner_rank[j] records which MPI rank owns point j
|
||||
// All ranks traverse the same block list so they all agree on ownership
|
||||
int *owner_rank;
|
||||
owner_rank = new int[NN];
|
||||
for (int j = 0; j < NN; j++)
|
||||
owner_rank[j] = -1;
|
||||
// we use weight to monitor code, later some day we can move it for optimization
|
||||
int *weight;
|
||||
weight = new int[NN];
|
||||
memset(weight, 0, sizeof(int) * NN);
|
||||
|
||||
double *DH, *llb, *uub;
|
||||
DH = new double[dim];
|
||||
|
||||
double DH[dim];
|
||||
for (int i = 0; i < dim; i++)
|
||||
{
|
||||
DH[i] = getdX(i);
|
||||
BlockBinIndex block_index;
|
||||
build_block_bin_index(this, DH, block_index);
|
||||
}
|
||||
llb = new double[dim];
|
||||
uub = new double[dim];
|
||||
|
||||
for (int j = 0; j < NN; j++) // run along points
|
||||
{
|
||||
@@ -557,11 +394,45 @@ void Patch::Interp_Points(MyList<var> *VarList,
|
||||
}
|
||||
}
|
||||
|
||||
const int block_i = find_block_index_for_point(block_index, pox, DH);
|
||||
if (block_i >= 0)
|
||||
MyList<Block> *Bp = blb;
|
||||
bool notfind = true;
|
||||
while (notfind && Bp) // run along Blocks
|
||||
{
|
||||
Block *BP = block_index.views[block_i].bp;
|
||||
owner_rank[j] = BP->rank;
|
||||
Block *BP = Bp->data;
|
||||
|
||||
bool flag = true;
|
||||
for (int i = 0; i < dim; i++)
|
||||
{
|
||||
// NOTE: our dividing structure is (exclude ghost)
|
||||
// -1 0
|
||||
// 1 2
|
||||
// so (0,1) does not belong to any part for vertex structure
|
||||
// here we put (0,0.5) to left part and (0.5,1) to right part
|
||||
// BUT for cell structure the bbox is (-1.5,0.5) and (0.5,2.5), there is no missing region at all
|
||||
#ifdef Vertex
|
||||
#ifdef Cell
|
||||
#error Both Cell and Vertex are defined
|
||||
#endif
|
||||
llb[i] = (feq(BP->bbox[i], bbox[i], DH[i] / 2)) ? BP->bbox[i] + lli[i] * DH[i] : BP->bbox[i] + (ghost_width - 0.5) * DH[i];
|
||||
uub[i] = (feq(BP->bbox[dim + i], bbox[dim + i], DH[i] / 2)) ? BP->bbox[dim + i] - uui[i] * DH[i] : BP->bbox[dim + i] - (ghost_width - 0.5) * DH[i];
|
||||
#else
|
||||
#ifdef Cell
|
||||
llb[i] = (feq(BP->bbox[i], bbox[i], DH[i] / 2)) ? BP->bbox[i] + lli[i] * DH[i] : BP->bbox[i] + ghost_width * DH[i];
|
||||
uub[i] = (feq(BP->bbox[dim + i], bbox[dim + i], DH[i] / 2)) ? BP->bbox[dim + i] - uui[i] * DH[i] : BP->bbox[dim + i] - ghost_width * DH[i];
|
||||
#else
|
||||
#error Not define Vertex nor Cell
|
||||
#endif
|
||||
#endif
|
||||
if (XX[i][j] - llb[i] < -DH[i] / 2 || XX[i][j] - uub[i] > DH[i] / 2)
|
||||
{
|
||||
flag = false;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if (flag)
|
||||
{
|
||||
notfind = false;
|
||||
if (myrank == BP->rank)
|
||||
{
|
||||
//---> interpolation
|
||||
@@ -569,338 +440,119 @@ void Patch::Interp_Points(MyList<var> *VarList,
|
||||
int k = 0;
|
||||
while (varl) // run along variables
|
||||
{
|
||||
f_global_interp(BP->shape, BP->X[0], BP->X[1], BP->X[2], BP->fgfs[varl->data->sgfn], Shellf[j * num_var + k],
|
||||
// shellf[j*num_var+k] = Parallel::global_interp(dim,BP->shape,BP->X,BP->fgfs[varl->data->sgfn],
|
||||
// pox,ordn,varl->data->SoA,Symmetry);
|
||||
f_global_interp(BP->shape, BP->X[0], BP->X[1], BP->X[2], BP->fgfs[varl->data->sgfn], shellf[j * num_var + k],
|
||||
pox[0], pox[1], pox[2], ordn, varl->data->SoA, Symmetry);
|
||||
varl = varl->next;
|
||||
k++;
|
||||
}
|
||||
weight[j] = 1;
|
||||
}
|
||||
}
|
||||
if (Bp == ble)
|
||||
break;
|
||||
Bp = Bp->next;
|
||||
}
|
||||
}
|
||||
|
||||
// Replace MPI_Allreduce with per-owner MPI_Bcast:
|
||||
// Group consecutive points by owner rank and broadcast each group.
|
||||
// Since each point's data is non-zero only on the owner rank,
|
||||
// Bcast from owner is equivalent to Allreduce(MPI_SUM) but much cheaper.
|
||||
MPI_Allreduce(shellf, Shellf, NN * num_var, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
|
||||
int *Weight;
|
||||
Weight = new int[NN];
|
||||
MPI_Allreduce(weight, Weight, NN, MPI_INT, MPI_SUM, MPI_COMM_WORLD);
|
||||
|
||||
// misc::tillherecheck("print me");
|
||||
|
||||
for (int i = 0; i < NN; i++)
|
||||
{
|
||||
int j = 0;
|
||||
while (j < NN)
|
||||
{
|
||||
int cur_owner = owner_rank[j];
|
||||
if (cur_owner < 0)
|
||||
if (Weight[i] > 1)
|
||||
{
|
||||
if (myrank == 0)
|
||||
cout << "WARNING: Patch::Interp_Points meets multiple weight" << endl;
|
||||
for (int j = 0; j < num_var; j++)
|
||||
Shellf[j + i * num_var] = Shellf[j + i * num_var] / Weight[i];
|
||||
}
|
||||
else if (Weight[i] == 0 && myrank == 0)
|
||||
{
|
||||
cout << "ERROR: Patch::Interp_Points fails to find point (";
|
||||
for (int d = 0; d < dim; d++)
|
||||
for (int j = 0; j < dim; j++)
|
||||
{
|
||||
cout << XX[d][j];
|
||||
if (d < dim - 1)
|
||||
cout << XX[j][i];
|
||||
if (j < dim - 1)
|
||||
cout << ",";
|
||||
else
|
||||
cout << ")";
|
||||
}
|
||||
cout << " on Patch (";
|
||||
for (int d = 0; d < dim; d++)
|
||||
for (int j = 0; j < dim; j++)
|
||||
{
|
||||
cout << bbox[d] << "+" << lli[d] * DH[d];
|
||||
if (d < dim - 1)
|
||||
cout << bbox[j] << "+" << lli[j] * getdX(j);
|
||||
if (j < dim - 1)
|
||||
cout << ",";
|
||||
else
|
||||
cout << ")--";
|
||||
}
|
||||
cout << "(";
|
||||
for (int d = 0; d < dim; d++)
|
||||
for (int j = 0; j < dim; j++)
|
||||
{
|
||||
cout << bbox[dim + d] << "-" << uui[d] * DH[d];
|
||||
if (d < dim - 1)
|
||||
cout << bbox[dim + j] << "-" << uui[j] * getdX(j);
|
||||
if (j < dim - 1)
|
||||
cout << ",";
|
||||
else
|
||||
cout << ")" << endl;
|
||||
}
|
||||
MPI_Abort(MPI_COMM_WORLD, 1);
|
||||
}
|
||||
j++;
|
||||
continue;
|
||||
}
|
||||
// Find contiguous run of points with the same owner
|
||||
int jstart = j;
|
||||
while (j < NN && owner_rank[j] == cur_owner)
|
||||
j++;
|
||||
int count = (j - jstart) * num_var;
|
||||
MPI_Bcast(Shellf + jstart * num_var, count, MPI_DOUBLE, cur_owner, MPI_COMM_WORLD);
|
||||
}
|
||||
}
|
||||
|
||||
delete[] owner_rank;
|
||||
}
|
||||
void Patch::Interp_Points(MyList<var> *VarList,
|
||||
int NN, double **XX,
|
||||
double *Shellf, int Symmetry,
|
||||
int Nmin_consumer, int Nmax_consumer)
|
||||
{
|
||||
// Targeted point-to-point overload: each owner sends each point only to
|
||||
// the one rank that needs it for integration (consumer), reducing
|
||||
// communication volume by ~nprocs times compared to the Bcast version.
|
||||
#ifdef INTERP_LB_PROFILE
|
||||
double t_interp_start = MPI_Wtime();
|
||||
#endif
|
||||
int myrank, nprocs;
|
||||
MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
|
||||
MPI_Comm_size(MPI_COMM_WORLD, &nprocs);
|
||||
|
||||
int ordn = 2 * ghost_width;
|
||||
MyList<var> *varl;
|
||||
int num_var = 0;
|
||||
varl = VarList;
|
||||
while (varl)
|
||||
#if 0
|
||||
checkBlock();
|
||||
#else
|
||||
cout << "splited domains:" << endl;
|
||||
{
|
||||
num_var++;
|
||||
varl = varl->next;
|
||||
}
|
||||
|
||||
memset(Shellf, 0, sizeof(double) * NN * num_var);
|
||||
|
||||
// owner_rank[j] records which MPI rank owns point j
|
||||
int *owner_rank;
|
||||
owner_rank = new int[NN];
|
||||
for (int j = 0; j < NN; j++)
|
||||
owner_rank[j] = -1;
|
||||
|
||||
double DH[dim];
|
||||
for (int i = 0; i < dim; i++)
|
||||
DH[i] = getdX(i);
|
||||
BlockBinIndex block_index;
|
||||
build_block_bin_index(this, DH, block_index);
|
||||
|
||||
// --- Interpolation phase (identical to original) ---
|
||||
for (int j = 0; j < NN; j++)
|
||||
MyList<Block> *Bp = blb;
|
||||
while (Bp)
|
||||
{
|
||||
double pox[dim];
|
||||
Block *BP = Bp->data;
|
||||
|
||||
for (int i = 0; i < dim; i++)
|
||||
{
|
||||
pox[i] = XX[i][j];
|
||||
if (myrank == 0 && (XX[i][j] < bbox[i] + lli[i] * DH[i] || XX[i][j] > bbox[dim + i] - uui[i] * DH[i]))
|
||||
{
|
||||
cout << "Patch::Interp_Points: point (";
|
||||
for (int k = 0; k < dim; k++)
|
||||
{
|
||||
cout << XX[k][j];
|
||||
if (k < dim - 1)
|
||||
cout << ",";
|
||||
else
|
||||
cout << ") is out of current Patch." << endl;
|
||||
}
|
||||
MPI_Abort(MPI_COMM_WORLD, 1);
|
||||
}
|
||||
}
|
||||
|
||||
const int block_i = find_block_index_for_point(block_index, pox, DH);
|
||||
if (block_i >= 0)
|
||||
{
|
||||
Block *BP = block_index.views[block_i].bp;
|
||||
owner_rank[j] = BP->rank;
|
||||
if (myrank == BP->rank)
|
||||
{
|
||||
varl = VarList;
|
||||
int k = 0;
|
||||
while (varl)
|
||||
{
|
||||
f_global_interp(BP->shape, BP->X[0], BP->X[1], BP->X[2], BP->fgfs[varl->data->sgfn], Shellf[j * num_var + k],
|
||||
pox[0], pox[1], pox[2], ordn, varl->data->SoA, Symmetry);
|
||||
varl = varl->next;
|
||||
k++;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#ifdef INTERP_LB_PROFILE
|
||||
double t_interp_end = MPI_Wtime();
|
||||
double t_interp_local = t_interp_end - t_interp_start;
|
||||
#ifdef Vertex
|
||||
#ifdef Cell
|
||||
#error Both Cell and Vertex are defined
|
||||
#endif
|
||||
llb[i] = (feq(BP->bbox[i], bbox[i], DH[i] / 2)) ? BP->bbox[i] + lli[i] * DH[i] : BP->bbox[i] + (ghost_width - 0.5) * DH[i];
|
||||
uub[i] = (feq(BP->bbox[dim + i], bbox[dim + i], DH[i] / 2)) ? BP->bbox[dim + i] - uui[i] * DH[i] : BP->bbox[dim + i] - (ghost_width - 0.5) * DH[i];
|
||||
#else
|
||||
#ifdef Cell
|
||||
llb[i] = (feq(BP->bbox[i], bbox[i], DH[i] / 2)) ? BP->bbox[i] + lli[i] * DH[i] : BP->bbox[i] + ghost_width * DH[i];
|
||||
uub[i] = (feq(BP->bbox[dim + i], bbox[dim + i], DH[i] / 2)) ? BP->bbox[dim + i] - uui[i] * DH[i] : BP->bbox[dim + i] - ghost_width * DH[i];
|
||||
#else
|
||||
#error Not define Vertex nor Cell
|
||||
#endif
|
||||
#endif
|
||||
|
||||
// --- Error check for unfound points ---
|
||||
for (int j = 0; j < NN; j++)
|
||||
{
|
||||
if (owner_rank[j] < 0 && myrank == 0)
|
||||
{
|
||||
cout << "ERROR: Patch::Interp_Points fails to find point (";
|
||||
for (int d = 0; d < dim; d++)
|
||||
{
|
||||
cout << XX[d][j];
|
||||
if (d < dim - 1)
|
||||
cout << ",";
|
||||
else
|
||||
cout << ")";
|
||||
}
|
||||
cout << " on Patch (";
|
||||
for (int d = 0; d < dim; d++)
|
||||
{
|
||||
cout << bbox[d] << "+" << lli[d] * DH[d];
|
||||
if (d < dim - 1)
|
||||
cout << ",";
|
||||
else
|
||||
cout << ")--";
|
||||
}
|
||||
cout << "(";
|
||||
for (int d = 0; d < dim; d++)
|
||||
for (int j = 0; j < dim; j++)
|
||||
{
|
||||
cout << bbox[dim + d] << "-" << uui[d] * DH[d];
|
||||
if (d < dim - 1)
|
||||
cout << llb[j] << ":" << uub[j];
|
||||
if (j < dim - 1)
|
||||
cout << ",";
|
||||
else
|
||||
cout << ")" << endl;
|
||||
}
|
||||
if (Bp == ble)
|
||||
break;
|
||||
Bp = Bp->next;
|
||||
}
|
||||
}
|
||||
#endif
|
||||
MPI_Abort(MPI_COMM_WORLD, 1);
|
||||
}
|
||||
}
|
||||
|
||||
// --- Targeted point-to-point communication phase ---
|
||||
// Compute consumer_rank[j] using the same deterministic formula as surface_integral
|
||||
int *consumer_rank = new int[NN];
|
||||
{
|
||||
int mp = NN / nprocs;
|
||||
int Lp = NN - nprocs * mp;
|
||||
for (int j = 0; j < NN; j++)
|
||||
{
|
||||
if (j < Lp * (mp + 1))
|
||||
consumer_rank[j] = j / (mp + 1);
|
||||
else
|
||||
consumer_rank[j] = Lp + (j - Lp * (mp + 1)) / mp;
|
||||
}
|
||||
}
|
||||
|
||||
// Count sends and recvs per rank
|
||||
int *send_count = new int[nprocs];
|
||||
int *recv_count = new int[nprocs];
|
||||
memset(send_count, 0, sizeof(int) * nprocs);
|
||||
memset(recv_count, 0, sizeof(int) * nprocs);
|
||||
|
||||
for (int j = 0; j < NN; j++)
|
||||
{
|
||||
int own = owner_rank[j];
|
||||
int con = consumer_rank[j];
|
||||
if (own == con)
|
||||
continue; // local — no communication needed
|
||||
if (own == myrank)
|
||||
send_count[con]++;
|
||||
if (con == myrank)
|
||||
recv_count[own]++;
|
||||
}
|
||||
|
||||
// Build send buffers: for each destination rank, pack (index, data) pairs
|
||||
// Each entry: 1 int (point index j) + num_var doubles
|
||||
int total_send = 0, total_recv = 0;
|
||||
int *send_offset = new int[nprocs];
|
||||
int *recv_offset = new int[nprocs];
|
||||
for (int r = 0; r < nprocs; r++)
|
||||
{
|
||||
send_offset[r] = total_send;
|
||||
total_send += send_count[r];
|
||||
recv_offset[r] = total_recv;
|
||||
total_recv += recv_count[r];
|
||||
}
|
||||
|
||||
// Pack send buffers: each message contains (j, data[0..num_var-1]) per point
|
||||
int stride = 1 + num_var; // 1 double for index + num_var doubles for data
|
||||
double *sendbuf = new double[total_send * stride];
|
||||
double *recvbuf = new double[total_recv * stride];
|
||||
|
||||
// Temporary counters for packing
|
||||
int *pack_pos = new int[nprocs];
|
||||
memset(pack_pos, 0, sizeof(int) * nprocs);
|
||||
|
||||
for (int j = 0; j < NN; j++)
|
||||
{
|
||||
int own = owner_rank[j];
|
||||
int con = consumer_rank[j];
|
||||
if (own != myrank || con == myrank)
|
||||
continue;
|
||||
int pos = (send_offset[con] + pack_pos[con]) * stride;
|
||||
sendbuf[pos] = (double)j; // point index
|
||||
for (int v = 0; v < num_var; v++)
|
||||
sendbuf[pos + 1 + v] = Shellf[j * num_var + v];
|
||||
pack_pos[con]++;
|
||||
}
|
||||
|
||||
// Post non-blocking recvs and sends
|
||||
int n_req = 0;
|
||||
for (int r = 0; r < nprocs; r++)
|
||||
{
|
||||
if (recv_count[r] > 0) n_req++;
|
||||
if (send_count[r] > 0) n_req++;
|
||||
}
|
||||
|
||||
MPI_Request *reqs = new MPI_Request[n_req];
|
||||
int req_idx = 0;
|
||||
|
||||
for (int r = 0; r < nprocs; r++)
|
||||
{
|
||||
if (recv_count[r] > 0)
|
||||
{
|
||||
MPI_Irecv(recvbuf + recv_offset[r] * stride,
|
||||
recv_count[r] * stride, MPI_DOUBLE,
|
||||
r, 0, MPI_COMM_WORLD, &reqs[req_idx++]);
|
||||
}
|
||||
}
|
||||
for (int r = 0; r < nprocs; r++)
|
||||
{
|
||||
if (send_count[r] > 0)
|
||||
{
|
||||
MPI_Isend(sendbuf + send_offset[r] * stride,
|
||||
send_count[r] * stride, MPI_DOUBLE,
|
||||
r, 0, MPI_COMM_WORLD, &reqs[req_idx++]);
|
||||
}
|
||||
}
|
||||
|
||||
if (n_req > 0)
|
||||
MPI_Waitall(n_req, reqs, MPI_STATUSES_IGNORE);
|
||||
|
||||
// Unpack recv buffers into Shellf
|
||||
for (int i = 0; i < total_recv; i++)
|
||||
{
|
||||
int pos = i * stride;
|
||||
int j = (int)recvbuf[pos];
|
||||
for (int v = 0; v < num_var; v++)
|
||||
Shellf[j * num_var + v] = recvbuf[pos + 1 + v];
|
||||
}
|
||||
|
||||
delete[] reqs;
|
||||
delete[] sendbuf;
|
||||
delete[] recvbuf;
|
||||
delete[] pack_pos;
|
||||
delete[] send_offset;
|
||||
delete[] recv_offset;
|
||||
delete[] send_count;
|
||||
delete[] recv_count;
|
||||
delete[] consumer_rank;
|
||||
delete[] owner_rank;
|
||||
|
||||
#ifdef INTERP_LB_PROFILE
|
||||
{
|
||||
static bool profile_written = false;
|
||||
if (!profile_written) {
|
||||
double *all_times = nullptr;
|
||||
if (myrank == 0) all_times = new double[nprocs];
|
||||
MPI_Gather(&t_interp_local, 1, MPI_DOUBLE,
|
||||
all_times, 1, MPI_DOUBLE, 0, MPI_COMM_WORLD);
|
||||
if (myrank == 0) {
|
||||
int heavy[64];
|
||||
int nh = InterpLBProfile::identify_heavy_ranks(
|
||||
all_times, nprocs, 2.5, heavy, 64);
|
||||
InterpLBProfile::write_profile(
|
||||
"interp_lb_profile.bin", nprocs,
|
||||
all_times, heavy, nh, 2.5);
|
||||
printf("[InterpLB] Profile written: %d heavy ranks\n", nh);
|
||||
for (int i = 0; i < nh; i++)
|
||||
printf(" Heavy rank %d: %.6f s\n", heavy[i], all_times[heavy[i]]);
|
||||
delete[] all_times;
|
||||
}
|
||||
profile_written = true;
|
||||
}
|
||||
}
|
||||
#endif
|
||||
delete[] shellf;
|
||||
delete[] weight;
|
||||
delete[] Weight;
|
||||
delete[] DH;
|
||||
delete[] llb;
|
||||
delete[] uub;
|
||||
}
|
||||
void Patch::Interp_Points(MyList<var> *VarList,
|
||||
int NN, double **XX,
|
||||
@@ -921,24 +573,24 @@ void Patch::Interp_Points(MyList<var> *VarList,
|
||||
varl = varl->next;
|
||||
}
|
||||
|
||||
memset(Shellf, 0, sizeof(double) * NN * num_var);
|
||||
double *shellf;
|
||||
shellf = new double[NN * num_var];
|
||||
memset(shellf, 0, sizeof(double) * NN * num_var);
|
||||
|
||||
// owner_rank[j] stores the global rank that owns point j
|
||||
int *owner_rank;
|
||||
owner_rank = new int[NN];
|
||||
for (int j = 0; j < NN; j++)
|
||||
owner_rank[j] = -1;
|
||||
// we use weight to monitor code, later some day we can move it for optimization
|
||||
int *weight;
|
||||
weight = new int[NN];
|
||||
memset(weight, 0, sizeof(int) * NN);
|
||||
|
||||
// Build global-to-local rank translation for Comm_here
|
||||
MPI_Group world_group, local_group;
|
||||
MPI_Comm_group(MPI_COMM_WORLD, &world_group);
|
||||
MPI_Comm_group(Comm_here, &local_group);
|
||||
double *DH, *llb, *uub;
|
||||
DH = new double[dim];
|
||||
|
||||
double DH[dim];
|
||||
for (int i = 0; i < dim; i++)
|
||||
{
|
||||
DH[i] = getdX(i);
|
||||
BlockBinIndex block_index;
|
||||
build_block_bin_index(this, DH, block_index);
|
||||
}
|
||||
llb = new double[dim];
|
||||
uub = new double[dim];
|
||||
|
||||
for (int j = 0; j < NN; j++) // run along points
|
||||
{
|
||||
@@ -961,11 +613,45 @@ void Patch::Interp_Points(MyList<var> *VarList,
|
||||
}
|
||||
}
|
||||
|
||||
const int block_i = find_block_index_for_point(block_index, pox, DH);
|
||||
if (block_i >= 0)
|
||||
MyList<Block> *Bp = blb;
|
||||
bool notfind = true;
|
||||
while (notfind && Bp) // run along Blocks
|
||||
{
|
||||
Block *BP = block_index.views[block_i].bp;
|
||||
owner_rank[j] = BP->rank;
|
||||
Block *BP = Bp->data;
|
||||
|
||||
bool flag = true;
|
||||
for (int i = 0; i < dim; i++)
|
||||
{
|
||||
// NOTE: our dividing structure is (exclude ghost)
|
||||
// -1 0
|
||||
// 1 2
|
||||
// so (0,1) does not belong to any part for vertex structure
|
||||
// here we put (0,0.5) to left part and (0.5,1) to right part
|
||||
// BUT for cell structure the bbox is (-1.5,0.5) and (0.5,2.5), there is no missing region at all
|
||||
#ifdef Vertex
|
||||
#ifdef Cell
|
||||
#error Both Cell and Vertex are defined
|
||||
#endif
|
||||
llb[i] = (feq(BP->bbox[i], bbox[i], DH[i] / 2)) ? BP->bbox[i] + lli[i] * DH[i] : BP->bbox[i] + (ghost_width - 0.5) * DH[i];
|
||||
uub[i] = (feq(BP->bbox[dim + i], bbox[dim + i], DH[i] / 2)) ? BP->bbox[dim + i] - uui[i] * DH[i] : BP->bbox[dim + i] - (ghost_width - 0.5) * DH[i];
|
||||
#else
|
||||
#ifdef Cell
|
||||
llb[i] = (feq(BP->bbox[i], bbox[i], DH[i] / 2)) ? BP->bbox[i] + lli[i] * DH[i] : BP->bbox[i] + ghost_width * DH[i];
|
||||
uub[i] = (feq(BP->bbox[dim + i], bbox[dim + i], DH[i] / 2)) ? BP->bbox[dim + i] - uui[i] * DH[i] : BP->bbox[dim + i] - ghost_width * DH[i];
|
||||
#else
|
||||
#error Not define Vertex nor Cell
|
||||
#endif
|
||||
#endif
|
||||
if (XX[i][j] - llb[i] < -DH[i] / 2 || XX[i][j] - uub[i] > DH[i] / 2)
|
||||
{
|
||||
flag = false;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if (flag)
|
||||
{
|
||||
notfind = false;
|
||||
if (myrank == BP->rank)
|
||||
{
|
||||
//---> interpolation
|
||||
@@ -973,44 +659,113 @@ void Patch::Interp_Points(MyList<var> *VarList,
|
||||
int k = 0;
|
||||
while (varl) // run along variables
|
||||
{
|
||||
f_global_interp(BP->shape, BP->X[0], BP->X[1], BP->X[2], BP->fgfs[varl->data->sgfn], Shellf[j * num_var + k],
|
||||
// shellf[j*num_var+k] = Parallel::global_interp(dim,BP->shape,BP->X,BP->fgfs[varl->data->sgfn],
|
||||
// pox,ordn,varl->data->SoA,Symmetry);
|
||||
f_global_interp(BP->shape, BP->X[0], BP->X[1], BP->X[2], BP->fgfs[varl->data->sgfn], shellf[j * num_var + k],
|
||||
pox[0], pox[1], pox[2], ordn, varl->data->SoA, Symmetry);
|
||||
varl = varl->next;
|
||||
k++;
|
||||
}
|
||||
weight[j] = 1;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Collect unique global owner ranks and translate to local ranks in Comm_here
|
||||
// Then broadcast each owner's points via MPI_Bcast on Comm_here
|
||||
{
|
||||
int j = 0;
|
||||
while (j < NN)
|
||||
{
|
||||
int cur_owner_global = owner_rank[j];
|
||||
if (cur_owner_global < 0)
|
||||
{
|
||||
// Point not found — skip (error check disabled for sub-communicator levels)
|
||||
j++;
|
||||
continue;
|
||||
}
|
||||
// Translate global rank to local rank in Comm_here
|
||||
int cur_owner_local;
|
||||
MPI_Group_translate_ranks(world_group, 1, &cur_owner_global, local_group, &cur_owner_local);
|
||||
|
||||
// Find contiguous run of points with the same owner
|
||||
int jstart = j;
|
||||
while (j < NN && owner_rank[j] == cur_owner_global)
|
||||
j++;
|
||||
int count = (j - jstart) * num_var;
|
||||
MPI_Bcast(Shellf + jstart * num_var, count, MPI_DOUBLE, cur_owner_local, Comm_here);
|
||||
if (Bp == ble)
|
||||
break;
|
||||
Bp = Bp->next;
|
||||
}
|
||||
}
|
||||
|
||||
MPI_Group_free(&world_group);
|
||||
MPI_Group_free(&local_group);
|
||||
delete[] owner_rank;
|
||||
MPI_Allreduce(shellf, Shellf, NN * num_var, MPI_DOUBLE, MPI_SUM, Comm_here);
|
||||
int *Weight;
|
||||
Weight = new int[NN];
|
||||
MPI_Allreduce(weight, Weight, NN, MPI_INT, MPI_SUM, Comm_here);
|
||||
|
||||
// misc::tillherecheck("print me");
|
||||
// if(lmyrank == 0) cout<<"myrank = "<<myrank<<"print me"<<endl;
|
||||
|
||||
for (int i = 0; i < NN; i++)
|
||||
{
|
||||
if (Weight[i] > 1)
|
||||
{
|
||||
if (lmyrank == 0)
|
||||
cout << "WARNING: Patch::Interp_Points meets multiple weight" << endl;
|
||||
for (int j = 0; j < num_var; j++)
|
||||
Shellf[j + i * num_var] = Shellf[j + i * num_var] / Weight[i];
|
||||
}
|
||||
#if 0 // for not involved levels, this may fail
|
||||
else if(Weight[i] == 0 && lmyrank == 0)
|
||||
{
|
||||
cout<<"ERROR: Patch::Interp_Points fails to find point (";
|
||||
for(int j=0;j<dim;j++)
|
||||
{
|
||||
cout<<XX[j][i];
|
||||
if(j<dim-1) cout<<",";
|
||||
else cout<<")";
|
||||
}
|
||||
cout<<" on Patch (";
|
||||
for(int j=0;j<dim;j++)
|
||||
{
|
||||
cout<<bbox[j]<<"+"<<lli[j]*getdX(j);
|
||||
if(j<dim-1) cout<<",";
|
||||
else cout<<")--";
|
||||
}
|
||||
cout<<"(";
|
||||
for(int j=0;j<dim;j++)
|
||||
{
|
||||
cout<<bbox[dim+j]<<"-"<<uui[j]*getdX(j);
|
||||
if(j<dim-1) cout<<",";
|
||||
else cout<<")"<<endl;
|
||||
}
|
||||
#if 0
|
||||
checkBlock();
|
||||
#else
|
||||
cout<<"splited domains:"<<endl;
|
||||
{
|
||||
MyList<Block> *Bp=blb;
|
||||
while(Bp)
|
||||
{
|
||||
Block *BP=Bp->data;
|
||||
|
||||
for(int i=0;i<dim;i++)
|
||||
{
|
||||
#ifdef Vertex
|
||||
#ifdef Cell
|
||||
#error Both Cell and Vertex are defined
|
||||
#endif
|
||||
llb[i] = (feq(BP->bbox[i] ,bbox[i] ,DH[i]/2)) ? BP->bbox[i]+lli[i]*DH[i] : BP->bbox[i] +(ghost_width-0.5)*DH[i];
|
||||
uub[i] = (feq(BP->bbox[dim+i],bbox[dim+i],DH[i]/2)) ? BP->bbox[dim+i]-uui[i]*DH[i] : BP->bbox[dim+i]-(ghost_width-0.5)*DH[i];
|
||||
#else
|
||||
#ifdef Cell
|
||||
llb[i] = (feq(BP->bbox[i] ,bbox[i] ,DH[i]/2)) ? BP->bbox[i]+lli[i]*DH[i] : BP->bbox[i] +ghost_width*DH[i];
|
||||
uub[i] = (feq(BP->bbox[dim+i],bbox[dim+i],DH[i]/2)) ? BP->bbox[dim+i]-uui[i]*DH[i] : BP->bbox[dim+i]-ghost_width*DH[i];
|
||||
#else
|
||||
#error Not define Vertex nor Cell
|
||||
#endif
|
||||
#endif
|
||||
}
|
||||
cout<<"(";
|
||||
for(int j=0;j<dim;j++)
|
||||
{
|
||||
cout<<llb[j]<<":"<<uub[j];
|
||||
if(j<dim-1) cout<<",";
|
||||
else cout<<")"<<endl;
|
||||
}
|
||||
if(Bp == ble) break;
|
||||
Bp=Bp->next;
|
||||
}
|
||||
}
|
||||
#endif
|
||||
MPI_Abort(MPI_COMM_WORLD,1);
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
delete[] shellf;
|
||||
delete[] weight;
|
||||
delete[] Weight;
|
||||
delete[] DH;
|
||||
delete[] llb;
|
||||
delete[] uub;
|
||||
}
|
||||
void Patch::checkBlock()
|
||||
{
|
||||
@@ -39,10 +39,6 @@ public:
|
||||
|
||||
bool Find_Point(double *XX);
|
||||
|
||||
void Interp_Points(MyList<var> *VarList,
|
||||
int NN, double **XX,
|
||||
double *Shellf, int Symmetry,
|
||||
int Nmin_consumer, int Nmax_consumer);
|
||||
void Interp_Points(MyList<var> *VarList,
|
||||
int NN, double **XX,
|
||||
double *Shellf, int Symmetry, MPI_Comm Comm_here);
|
||||
File diff suppressed because it is too large
Load Diff
@@ -32,16 +32,6 @@ namespace Parallel
|
||||
int partition2(int *nxy, int split_size, int *min_width, int cpusize, int *shape); // special for 2 diemnsions
|
||||
int partition3(int *nxyz, int split_size, int *min_width, int cpusize, int *shape);
|
||||
MyList<Block> *distribute(MyList<Patch> *PatchLIST, int cpusize, int ingfsi, int fngfs, bool periodic, int nodes = 0); // produce corresponding Blocks
|
||||
MyList<Block> *distribute_optimize(MyList<Patch> *PatchLIST, int cpusize, int ingfsi, int fngfs, bool periodic, int nodes = 0);
|
||||
Block* splitHotspotBlock(MyList<Block>* &BlL, int _dim,
|
||||
int ib0_orig, int ib3_orig,
|
||||
int jb1_orig, int jb4_orig,
|
||||
int kb2_orig, int kb5_orig,
|
||||
Patch* PP, int r_left, int r_right,
|
||||
int ingfsi, int fngfsi, bool periodic,
|
||||
Block* &split_first_block, Block* &split_last_block);
|
||||
Block* createMappedBlock(MyList<Block>* &BlL, int _dim, int* shape, double* bbox,
|
||||
int block_id, int ingfsi, int fngfsi, int lev);
|
||||
void KillBlocks(MyList<Patch> *PatchLIST);
|
||||
|
||||
void setfunction(MyList<Block> *BlL, var *vn, double func(double x, double y, double z));
|
||||
@@ -91,49 +81,6 @@ namespace Parallel
|
||||
int Symmetry);
|
||||
void Sync(Patch *Pat, MyList<var> *VarList, int Symmetry);
|
||||
void Sync(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry);
|
||||
void Sync_merged(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry);
|
||||
|
||||
struct SyncCache {
|
||||
bool valid;
|
||||
int cpusize;
|
||||
MyList<gridseg> **combined_src;
|
||||
MyList<gridseg> **combined_dst;
|
||||
int *send_lengths;
|
||||
int *recv_lengths;
|
||||
double **send_bufs;
|
||||
double **recv_bufs;
|
||||
int *send_buf_caps;
|
||||
int *recv_buf_caps;
|
||||
MPI_Request *reqs;
|
||||
MPI_Status *stats;
|
||||
int max_reqs;
|
||||
bool lengths_valid;
|
||||
int *tc_req_node;
|
||||
int *tc_req_is_recv;
|
||||
int *tc_completed;
|
||||
SyncCache();
|
||||
void invalidate();
|
||||
void destroy();
|
||||
};
|
||||
|
||||
void Sync_cached(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry, SyncCache &cache);
|
||||
void transfer_cached(MyList<gridseg> **src, MyList<gridseg> **dst,
|
||||
MyList<var> *VarList1, MyList<var> *VarList2,
|
||||
int Symmetry, SyncCache &cache);
|
||||
|
||||
struct AsyncSyncState {
|
||||
int req_no;
|
||||
bool active;
|
||||
int *req_node;
|
||||
int *req_is_recv;
|
||||
int pending_recv;
|
||||
AsyncSyncState() : req_no(0), active(false), req_node(0), req_is_recv(0), pending_recv(0) {}
|
||||
};
|
||||
|
||||
void Sync_start(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry,
|
||||
SyncCache &cache, AsyncSyncState &state);
|
||||
void Sync_finish(SyncCache &cache, AsyncSyncState &state,
|
||||
MyList<var> *VarList, int Symmetry);
|
||||
void OutBdLow2Hi(Patch *Patc, Patch *Patf,
|
||||
MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
|
||||
int Symmetry);
|
||||
@@ -146,15 +93,6 @@ namespace Parallel
|
||||
void OutBdLow2Himix(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
|
||||
MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
|
||||
int Symmetry);
|
||||
void Restrict_cached(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
|
||||
MyList<var> *VarList1, MyList<var> *VarList2,
|
||||
int Symmetry, SyncCache &cache);
|
||||
void OutBdLow2Hi_cached(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
|
||||
MyList<var> *VarList1, MyList<var> *VarList2,
|
||||
int Symmetry, SyncCache &cache);
|
||||
void OutBdLow2Himix_cached(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
|
||||
MyList<var> *VarList1, MyList<var> *VarList2,
|
||||
int Symmetry, SyncCache &cache);
|
||||
void Prolong(Patch *Patc, Patch *Patf,
|
||||
MyList<var> *VarList1 /* source */, MyList<var> *VarList2 /* target */,
|
||||
int Symmetry);
|
||||
@@ -183,7 +121,6 @@ namespace Parallel
|
||||
MyList<Parallel::gridseg> **out_src, MyList<Parallel::gridseg> **out_dst);
|
||||
void PeriodicBD(Patch *Pat, MyList<var> *VarList, int Symmetry);
|
||||
double L2Norm(Patch *Pat, var *vf);
|
||||
void L2Norm7(Patch *Pat, var **vf, double *norms);
|
||||
void checkgsl(MyList<Parallel::gridseg> *pp, bool first_only);
|
||||
void checkvarl(MyList<var> *pp, bool first_only);
|
||||
MyList<Parallel::gridseg> *divide_gsl(MyList<Parallel::gridseg> *p, Patch *Pat);
|
||||
@@ -219,7 +156,6 @@ namespace Parallel
|
||||
void checkpatchlist(MyList<Patch> *PatL, bool buflog);
|
||||
|
||||
double L2Norm(Patch *Pat, var *vf, MPI_Comm Comm_here);
|
||||
void L2Norm7(Patch *Pat, var **vf, double *norms, MPI_Comm Comm_here);
|
||||
bool PatList_Interp_Points(MyList<Patch> *PatL, MyList<var> *VarList,
|
||||
int NN, double **XX,
|
||||
double *Shellf, int Symmetry, MPI_Comm Comm_here);
|
||||
@@ -1,212 +0,0 @@
|
||||
#include "rungekutta4_rout.h"
|
||||
#include <cstdio>
|
||||
#include <cstdlib>
|
||||
#include <cstddef>
|
||||
#include <complex>
|
||||
#include <immintrin.h>
|
||||
|
||||
namespace {
|
||||
|
||||
inline void rk4_stage0(std::size_t n,
|
||||
const double *__restrict f0,
|
||||
const double *__restrict frhs,
|
||||
double *__restrict f1,
|
||||
double c) {
|
||||
std::size_t i = 0;
|
||||
#if defined(__AVX512F__)
|
||||
const __m512d vc = _mm512_set1_pd(c);
|
||||
for (; i + 7 < n; i += 8) {
|
||||
const __m512d v0 = _mm512_loadu_pd(f0 + i);
|
||||
const __m512d vr = _mm512_loadu_pd(frhs + i);
|
||||
_mm512_storeu_pd(f1 + i, _mm512_fmadd_pd(vc, vr, v0));
|
||||
}
|
||||
#elif defined(__AVX2__)
|
||||
const __m256d vc = _mm256_set1_pd(c);
|
||||
for (; i + 3 < n; i += 4) {
|
||||
const __m256d v0 = _mm256_loadu_pd(f0 + i);
|
||||
const __m256d vr = _mm256_loadu_pd(frhs + i);
|
||||
_mm256_storeu_pd(f1 + i, _mm256_fmadd_pd(vc, vr, v0));
|
||||
}
|
||||
#endif
|
||||
#pragma ivdep
|
||||
for (; i < n; ++i) {
|
||||
f1[i] = f0[i] + c * frhs[i];
|
||||
}
|
||||
}
|
||||
|
||||
inline void rk4_rhs_accum(std::size_t n,
|
||||
const double *__restrict f1,
|
||||
double *__restrict frhs) {
|
||||
std::size_t i = 0;
|
||||
#if defined(__AVX512F__)
|
||||
const __m512d v2 = _mm512_set1_pd(2.0);
|
||||
for (; i + 7 < n; i += 8) {
|
||||
const __m512d v1 = _mm512_loadu_pd(f1 + i);
|
||||
const __m512d vrhs = _mm512_loadu_pd(frhs + i);
|
||||
_mm512_storeu_pd(frhs + i, _mm512_fmadd_pd(v2, v1, vrhs));
|
||||
}
|
||||
#elif defined(__AVX2__)
|
||||
const __m256d v2 = _mm256_set1_pd(2.0);
|
||||
for (; i + 3 < n; i += 4) {
|
||||
const __m256d v1 = _mm256_loadu_pd(f1 + i);
|
||||
const __m256d vrhs = _mm256_loadu_pd(frhs + i);
|
||||
_mm256_storeu_pd(frhs + i, _mm256_fmadd_pd(v2, v1, vrhs));
|
||||
}
|
||||
#endif
|
||||
#pragma ivdep
|
||||
for (; i < n; ++i) {
|
||||
frhs[i] = frhs[i] + 2.0 * f1[i];
|
||||
}
|
||||
}
|
||||
|
||||
inline void rk4_f1_from_f0_f1(std::size_t n,
|
||||
const double *__restrict f0,
|
||||
double *__restrict f1,
|
||||
double c) {
|
||||
std::size_t i = 0;
|
||||
#if defined(__AVX512F__)
|
||||
const __m512d vc = _mm512_set1_pd(c);
|
||||
for (; i + 7 < n; i += 8) {
|
||||
const __m512d v0 = _mm512_loadu_pd(f0 + i);
|
||||
const __m512d v1 = _mm512_loadu_pd(f1 + i);
|
||||
_mm512_storeu_pd(f1 + i, _mm512_fmadd_pd(vc, v1, v0));
|
||||
}
|
||||
#elif defined(__AVX2__)
|
||||
const __m256d vc = _mm256_set1_pd(c);
|
||||
for (; i + 3 < n; i += 4) {
|
||||
const __m256d v0 = _mm256_loadu_pd(f0 + i);
|
||||
const __m256d v1 = _mm256_loadu_pd(f1 + i);
|
||||
_mm256_storeu_pd(f1 + i, _mm256_fmadd_pd(vc, v1, v0));
|
||||
}
|
||||
#endif
|
||||
#pragma ivdep
|
||||
for (; i < n; ++i) {
|
||||
f1[i] = f0[i] + c * f1[i];
|
||||
}
|
||||
}
|
||||
|
||||
inline void rk4_stage3(std::size_t n,
|
||||
const double *__restrict f0,
|
||||
double *__restrict f1,
|
||||
const double *__restrict frhs,
|
||||
double c) {
|
||||
std::size_t i = 0;
|
||||
#if defined(__AVX512F__)
|
||||
const __m512d vc = _mm512_set1_pd(c);
|
||||
for (; i + 7 < n; i += 8) {
|
||||
const __m512d v0 = _mm512_loadu_pd(f0 + i);
|
||||
const __m512d v1 = _mm512_loadu_pd(f1 + i);
|
||||
const __m512d vr = _mm512_loadu_pd(frhs + i);
|
||||
_mm512_storeu_pd(f1 + i, _mm512_fmadd_pd(vc, _mm512_add_pd(v1, vr), v0));
|
||||
}
|
||||
#elif defined(__AVX2__)
|
||||
const __m256d vc = _mm256_set1_pd(c);
|
||||
for (; i + 3 < n; i += 4) {
|
||||
const __m256d v0 = _mm256_loadu_pd(f0 + i);
|
||||
const __m256d v1 = _mm256_loadu_pd(f1 + i);
|
||||
const __m256d vr = _mm256_loadu_pd(frhs + i);
|
||||
_mm256_storeu_pd(f1 + i, _mm256_fmadd_pd(vc, _mm256_add_pd(v1, vr), v0));
|
||||
}
|
||||
#endif
|
||||
#pragma ivdep
|
||||
for (; i < n; ++i) {
|
||||
f1[i] = f0[i] + c * (f1[i] + frhs[i]);
|
||||
}
|
||||
}
|
||||
|
||||
} // namespace
|
||||
|
||||
extern "C" {
|
||||
|
||||
void f_rungekutta4_scalar(double &dT, double &f0, double &f1, double &f_rhs, int &RK4) {
|
||||
constexpr double F1o6 = 1.0 / 6.0;
|
||||
constexpr double HLF = 0.5;
|
||||
constexpr double TWO = 2.0;
|
||||
|
||||
switch (RK4) {
|
||||
case 0:
|
||||
f1 = f0 + HLF * dT * f_rhs;
|
||||
break;
|
||||
case 1:
|
||||
f_rhs = f_rhs + TWO * f1;
|
||||
f1 = f0 + HLF * dT * f1;
|
||||
break;
|
||||
case 2:
|
||||
f_rhs = f_rhs + TWO * f1;
|
||||
f1 = f0 + dT * f1;
|
||||
break;
|
||||
case 3:
|
||||
f1 = f0 + F1o6 * dT * (f1 + f_rhs);
|
||||
break;
|
||||
default:
|
||||
std::fprintf(stderr, "rungekutta4_scalar_c: invalid RK4 stage %d\n", RK4);
|
||||
std::abort();
|
||||
}
|
||||
}
|
||||
|
||||
void rungekutta4_cplxscalar_(double &dT,
|
||||
std::complex<double> &f0,
|
||||
std::complex<double> &f1,
|
||||
std::complex<double> &f_rhs,
|
||||
int &RK4) {
|
||||
constexpr double F1o6 = 1.0 / 6.0;
|
||||
constexpr double HLF = 0.5;
|
||||
constexpr double TWO = 2.0;
|
||||
|
||||
switch (RK4) {
|
||||
case 0:
|
||||
f1 = f0 + HLF * dT * f_rhs;
|
||||
break;
|
||||
case 1:
|
||||
f_rhs = f_rhs + TWO * f1;
|
||||
f1 = f0 + HLF * dT * f1;
|
||||
break;
|
||||
case 2:
|
||||
f_rhs = f_rhs + TWO * f1;
|
||||
f1 = f0 + dT * f1;
|
||||
break;
|
||||
case 3:
|
||||
f1 = f0 + F1o6 * dT * (f1 + f_rhs);
|
||||
break;
|
||||
default:
|
||||
std::fprintf(stderr, "rungekutta4_cplxscalar_c: invalid RK4 stage %d\n", RK4);
|
||||
std::abort();
|
||||
}
|
||||
}
|
||||
|
||||
int f_rungekutta4_rout(int *ex, double &dT,
|
||||
double *f0, double *f1, double *f_rhs,
|
||||
int &RK4) {
|
||||
const std::size_t n = static_cast<std::size_t>(ex[0]) *
|
||||
static_cast<std::size_t>(ex[1]) *
|
||||
static_cast<std::size_t>(ex[2]);
|
||||
const double *const __restrict f0r = f0;
|
||||
double *const __restrict f1r = f1;
|
||||
double *const __restrict frhs = f_rhs;
|
||||
|
||||
if (__builtin_expect(static_cast<unsigned>(RK4) > 3u, 0)) {
|
||||
std::fprintf(stderr, "rungekutta4_rout_c: invalid RK4 stage %d\n", RK4);
|
||||
std::abort();
|
||||
}
|
||||
|
||||
switch (RK4) {
|
||||
case 0:
|
||||
rk4_stage0(n, f0r, frhs, f1r, 0.5 * dT);
|
||||
break;
|
||||
case 1:
|
||||
rk4_rhs_accum(n, f1r, frhs);
|
||||
rk4_f1_from_f0_f1(n, f0r, f1r, 0.5 * dT);
|
||||
break;
|
||||
case 2:
|
||||
rk4_rhs_accum(n, f1r, frhs);
|
||||
rk4_f1_from_f0_f1(n, f0r, f1r, dT);
|
||||
break;
|
||||
default:
|
||||
rk4_stage3(n, f0r, f1r, frhs, (1.0 / 6.0) * dT);
|
||||
break;
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
} // extern "C"
|
||||
@@ -3472,43 +3472,6 @@ double ShellPatch::L2Norm(var *vf)
|
||||
|
||||
return tvf;
|
||||
}
|
||||
void ShellPatch::L2Norm7(var **vf, double *norms)
|
||||
{
|
||||
double tvf[7], dtvf[7];
|
||||
int BDW = overghost;
|
||||
for (int i = 0; i < 7; i++)
|
||||
dtvf[i] = 0;
|
||||
|
||||
MyList<ss_patch> *sPp = PatL;
|
||||
while (sPp)
|
||||
{
|
||||
MyList<Block> *Bp = sPp->data->blb;
|
||||
while (Bp)
|
||||
{
|
||||
Block *cg = Bp->data;
|
||||
if (myrank == cg->rank)
|
||||
{
|
||||
f_l2normhelper7(cg->shape, cg->X[0], cg->X[1], cg->X[2],
|
||||
sPp->data->bbox[0], sPp->data->bbox[1], sPp->data->bbox[2],
|
||||
sPp->data->bbox[3], sPp->data->bbox[4], sPp->data->bbox[5],
|
||||
cg->fgfs[vf[0]->sgfn], cg->fgfs[vf[1]->sgfn], cg->fgfs[vf[2]->sgfn],
|
||||
cg->fgfs[vf[3]->sgfn], cg->fgfs[vf[4]->sgfn], cg->fgfs[vf[5]->sgfn],
|
||||
cg->fgfs[vf[6]->sgfn], tvf, BDW);
|
||||
for (int i = 0; i < 7; i++)
|
||||
dtvf[i] += tvf[i];
|
||||
}
|
||||
if (Bp == sPp->data->ble)
|
||||
break;
|
||||
Bp = Bp->next;
|
||||
}
|
||||
sPp = sPp->next;
|
||||
}
|
||||
|
||||
MPI_Allreduce(dtvf, tvf, 7, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
|
||||
|
||||
for (int i = 0; i < 7; i++)
|
||||
norms[i] = sqrt(tvf[i]);
|
||||
}
|
||||
|
||||
// find maximum of abstract value, XX store position for maximum, Shellf store maximum themselvs
|
||||
void ShellPatch::Find_Maximum(MyList<var> *VarList, double *XX,
|
||||
@@ -198,7 +198,6 @@ public:
|
||||
void write_Pablo_file_ss(int *ext, double xmin, double xmax, double ymin, double ymax, double zmin, double zmax,
|
||||
char *filename, int sst);
|
||||
double L2Norm(var *vf);
|
||||
void L2Norm7(var **vf, double *norms);
|
||||
void Find_Maximum(MyList<var> *VarList, double *XX, double *Shellf);
|
||||
};
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,8 +1,7 @@
|
||||
|
||||
#ifndef TWO_PUNCTURES_H
|
||||
#define TWO_PUNCTURES_H
|
||||
|
||||
#include <omp.h>
|
||||
|
||||
#define StencilSize 19
|
||||
#define N_PlaneRelax 1
|
||||
#define NRELAX 200
|
||||
@@ -43,18 +42,6 @@ private:
|
||||
|
||||
int ntotal;
|
||||
|
||||
// ===== Precomputed spectral derivative matrices =====
|
||||
double *D1_A, *D2_A;
|
||||
double *D1_B, *D2_B;
|
||||
double *DF1_phi, *DF2_phi;
|
||||
|
||||
// ===== Pre-allocated workspace for LineRelax (per-thread) =====
|
||||
int max_threads;
|
||||
double **ws_diag_be, **ws_e_be, **ws_f_be, **ws_b_be, **ws_x_be;
|
||||
double **ws_l_be, **ws_u_be, **ws_d_be, **ws_y_be;
|
||||
double **ws_diag_al, **ws_e_al, **ws_f_al, **ws_b_al, **ws_x_al;
|
||||
double **ws_l_al, **ws_u_al, **ws_d_al, **ws_y_al;
|
||||
|
||||
struct parameters
|
||||
{
|
||||
int nvar, n1, n2, n3;
|
||||
@@ -71,28 +58,6 @@ public:
|
||||
int Newtonmaxit);
|
||||
~TwoPunctures();
|
||||
|
||||
// 02/07: New/modified methods
|
||||
void allocate_workspace();
|
||||
void free_workspace();
|
||||
void precompute_derivative_matrices();
|
||||
void build_cheb_deriv_matrices(int n, double *D1, double *D2);
|
||||
void build_fourier_deriv_matrices(int N, double *DF1, double *DF2);
|
||||
void Derivatives_AB3_MatMul(int nvar, int n1, int n2, int n3, derivs v);
|
||||
void ThomasAlgorithm_ws(int N, double *b, double *a, double *c, double *x, double *q,
|
||||
double *l, double *u_ws, double *d, double *y);
|
||||
void LineRelax_be_omp(double *dv,
|
||||
int const i, int const k, int const nvar,
|
||||
int const n1, int const n2, int const n3,
|
||||
double const *rhs, int const *ncols, int **cols,
|
||||
double **JFD, int tid);
|
||||
void LineRelax_al_omp(double *dv,
|
||||
int const j, int const k, int const nvar,
|
||||
int const n1, int const n2, int const n3,
|
||||
double const *rhs, int const *ncols,
|
||||
int **cols, double **JFD, int tid);
|
||||
void relax_omp(double *dv, int const nvar, int const n1, int const n2, int const n3,
|
||||
double const *rhs, int const *ncols, int **cols, double **JFD);
|
||||
|
||||
void Solve();
|
||||
void set_initial_guess(derivs v);
|
||||
int index(int i, int j, int k, int l, int a, int b, int c, int d);
|
||||
@@ -151,11 +116,23 @@ public:
|
||||
double BY_KKofxyz(double x, double y, double z);
|
||||
void SetMatrix_JFD(int nvar, int n1, int n2, int n3, derivs u, int *ncols, int **cols, double **Matrix);
|
||||
void J_times_dv(int nvar, int n1, int n2, int n3, derivs dv, double *Jdv, derivs u);
|
||||
void relax(double *dv, int const nvar, int const n1, int const n2, int const n3,
|
||||
double const *rhs, int const *ncols, int **cols, double **JFD);
|
||||
void LineRelax_be(double *dv,
|
||||
int const i, int const k, int const nvar,
|
||||
int const n1, int const n2, int const n3,
|
||||
double const *rhs, int const *ncols, int **cols,
|
||||
double **JFD);
|
||||
void JFD_times_dv(int i, int j, int k, int nvar, int n1, int n2,
|
||||
int n3, derivs dv, derivs u, double *values);
|
||||
void LinEquations(double A, double B, double X, double R,
|
||||
double x, double r, double phi,
|
||||
double y, double z, derivs dU, derivs U, double *values);
|
||||
void LineRelax_al(double *dv,
|
||||
int const j, int const k, int const nvar,
|
||||
int const n1, int const n2, int const n3,
|
||||
double const *rhs, int const *ncols,
|
||||
int **cols, double **JFD);
|
||||
void ThomasAlgorithm(int N, double *b, double *a, double *c, double *x, double *q);
|
||||
void Save(char *fname);
|
||||
// provided by Vasileios Paschalidis (vpaschal@illinois.edu)
|
||||
File diff suppressed because it is too large
Load Diff
@@ -48,7 +48,6 @@ public:
|
||||
double StartTime, TotalTime;
|
||||
double AnasTime, DumpTime, d2DumpTime, CheckTime;
|
||||
double LastAnas, LastConsOut;
|
||||
int *ConstraintRefreshLevels;
|
||||
double Courant;
|
||||
double numepss, numepsb, numepsh;
|
||||
int Symmetry;
|
||||
@@ -127,15 +126,8 @@ public:
|
||||
MyList<var> *OldStateList, *DumpList;
|
||||
MyList<var> *ConstraintList;
|
||||
|
||||
Parallel::SyncCache *sync_cache_pre; // per-level cache for predictor sync
|
||||
Parallel::SyncCache *sync_cache_cor; // per-level cache for corrector sync
|
||||
Parallel::SyncCache *sync_cache_rp_coarse; // RestrictProlong sync on PatL[lev-1]
|
||||
Parallel::SyncCache *sync_cache_rp_fine; // RestrictProlong sync on PatL[lev]
|
||||
Parallel::SyncCache *sync_cache_restrict; // cached Restrict in RestrictProlong
|
||||
Parallel::SyncCache *sync_cache_outbd; // cached OutBdLow2Hi in RestrictProlong
|
||||
|
||||
monitor *ErrorMonitor, *Psi4Monitor, *BHMonitor, *MAPMonitor;
|
||||
monitor *ConVMonitor, *TimingMonitor;
|
||||
monitor *ConVMonitor;
|
||||
surface_integral *Waveshell;
|
||||
checkpoint *CheckPoint;
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -32,19 +32,6 @@
|
||||
#define f_compute_rhs_Z4c_ss compute_rhs_z4c_ss_
|
||||
#define f_compute_constraint_fr compute_constraint_fr_
|
||||
#endif
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C"
|
||||
{
|
||||
#endif
|
||||
void f_bssn_rhs_kernel_timing_reset();
|
||||
int f_bssn_rhs_kernel_timing_bucket_count();
|
||||
const double *f_bssn_rhs_kernel_timing_local_seconds();
|
||||
const char *f_bssn_rhs_kernel_timing_label(int);
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
|
||||
extern "C"
|
||||
{
|
||||
int f_compute_rhs_bssn(int *, double &, double *, double *, double *, // ex,T,X,Y,Z
|
||||
@@ -130,11 +130,7 @@ void cgh::compose_cgh(int nprocs)
|
||||
for (int lev = 0; lev < levels; lev++)
|
||||
{
|
||||
checkPatchList(PatL[lev], false);
|
||||
#ifdef INTERP_LB_OPTIMIZE
|
||||
Parallel::distribute_optimize(PatL[lev], nprocs, ingfs, fngfs, false);
|
||||
#else
|
||||
Parallel::distribute(PatL[lev], nprocs, ingfs, fngfs, false);
|
||||
#endif
|
||||
#if (RPB == 1)
|
||||
// we need distributed box of PatL[lev] and PatL[lev-1]
|
||||
if (lev > 0)
|
||||
@@ -1305,13 +1301,13 @@ bool cgh::Interp_One_Point(MyList<var> *VarList,
|
||||
}
|
||||
|
||||
|
||||
bool cgh::Regrid_Onelevel(int lev, int Symmetry, int BH_num, double **Porgbr, double **Porg0,
|
||||
void cgh::Regrid_Onelevel(int lev, int Symmetry, int BH_num, double **Porgbr, double **Porg0,
|
||||
MyList<var> *OldList, MyList<var> *StateList,
|
||||
MyList<var> *FutureList, MyList<var> *tmList, bool BB,
|
||||
monitor *ErrorMonitor)
|
||||
{
|
||||
if (lev < movls)
|
||||
return false;
|
||||
return;
|
||||
|
||||
#if (0)
|
||||
// #if (PSTR == 1 || PSTR == 2)
|
||||
@@ -1400,7 +1396,7 @@ bool cgh::Regrid_Onelevel(int lev, int Symmetry, int BH_num, double **Porgbr, do
|
||||
for (bhi = 0; bhi < BH_num; bhi++)
|
||||
delete[] tmpPorg[bhi];
|
||||
delete[] tmpPorg;
|
||||
return false;
|
||||
return;
|
||||
}
|
||||
// x direction
|
||||
rr = (Porg0[bhi][0] - handle[lev][grd][0]) / dX;
|
||||
@@ -1504,7 +1500,6 @@ bool cgh::Regrid_Onelevel(int lev, int Symmetry, int BH_num, double **Porgbr, do
|
||||
for (int bhi = 0; bhi < BH_num; bhi++)
|
||||
delete[] tmpPorg[bhi];
|
||||
delete[] tmpPorg;
|
||||
return tot_flag;
|
||||
}
|
||||
|
||||
|
||||
@@ -74,7 +74,7 @@ public:
|
||||
MyList<var> *OldList, MyList<var> *StateList,
|
||||
MyList<var> *FutureList, MyList<var> *tmList,
|
||||
int Symmetry, bool BB);
|
||||
bool Regrid_Onelevel(int lev, int Symmetry, int BH_num, double **Porgbr, double **Porg0,
|
||||
void Regrid_Onelevel(int lev, int Symmetry, int BH_num, double **Porgbr, double **Porg0,
|
||||
MyList<var> *OldList, MyList<var> *StateList,
|
||||
MyList<var> *FutureList, MyList<var> *tmList, bool BB,
|
||||
monitor *ErrorMonitor);
|
||||
@@ -69,10 +69,12 @@
|
||||
fy = ZEO
|
||||
fz = ZEO
|
||||
|
||||
!DIR$ SIMD VECTORLENGTHFOR(KNOWN_INTEGER=8)
|
||||
!DIR$ UNROLL PARTIAL(4)
|
||||
! Intel compiler directives for aggressive vectorization
|
||||
!DIR$ SIMD
|
||||
!DIR$ IVDEP
|
||||
do k=1,ex(3)-1
|
||||
do j=1,ex(2)-1
|
||||
!DIR$ SIMD
|
||||
do i=1,ex(1)-1
|
||||
! x direction
|
||||
if(i+1 <= imax .and. i-1 >= imin)then
|
||||
@@ -373,8 +375,6 @@
|
||||
fxz = ZEO
|
||||
fyz = ZEO
|
||||
|
||||
!DIR$ SIMD VECTORLENGTHFOR(KNOWN_INTEGER=8)
|
||||
!DIR$ UNROLL PARTIAL(4)
|
||||
do k=1,ex(3)-1
|
||||
do j=1,ex(2)-1
|
||||
do i=1,ex(1)-1
|
||||
@@ -962,6 +962,7 @@
|
||||
real*8,dimension(-1:ex(1),-1:ex(2),-1:ex(3)) :: fh
|
||||
real*8, dimension(3) :: SoA
|
||||
integer :: imin,jmin,kmin,imax,jmax,kmax,i,j,k
|
||||
integer :: ib_s, ib_e, jb_s, jb_e, kb_s, kb_e
|
||||
real*8 :: d12dx,d12dy,d12dz,d2dx,d2dy,d2dz
|
||||
integer, parameter :: NO_SYMM = 0, EQ_SYMM = 1, OCTANT = 2
|
||||
real*8, parameter :: ZEO=0.d0,ONE=1.d0, F60=6.d1
|
||||
@@ -1001,105 +1002,66 @@
|
||||
fy = ZEO
|
||||
fz = ZEO
|
||||
|
||||
ib_s = max(1, imin + 2)
|
||||
ib_e = min(ex(1)-1, imax - 2)
|
||||
jb_s = max(1, jmin + 2)
|
||||
jb_e = min(ex(2)-1, jmax - 2)
|
||||
kb_s = max(1, kmin + 2)
|
||||
kb_e = min(ex(3)-1, kmax - 2)
|
||||
|
||||
! Intel compiler directives for aggressive vectorization
|
||||
!DIR$ SIMD
|
||||
!DIR$ IVDEP
|
||||
do k=1,ex(3)-1
|
||||
do j=1,ex(2)-1
|
||||
do i=1,ex(1)-1
|
||||
#if 0
|
||||
! x direction
|
||||
if(i+2 <= imax .and. i-2 >= imin)then
|
||||
!
|
||||
! f(i-2) - 8 f(i-1) + 8 f(i+1) - f(i+2)
|
||||
! fx(i) = ---------------------------------------------
|
||||
! 12 dx
|
||||
fx(i,j,k)=d12dx*(fh(i-2,j,k)-EIT*fh(i-1,j,k)+EIT*fh(i+1,j,k)-fh(i+2,j,k))
|
||||
|
||||
elseif(i+1 <= imax .and. i-1 >= imin)then
|
||||
!
|
||||
! - f(i-1) + f(i+1)
|
||||
! fx(i) = --------------------------------
|
||||
! 2 dx
|
||||
fx(i,j,k)=d2dx*(-fh(i-1,j,k)+fh(i+1,j,k))
|
||||
! Check if (j, k) are within the safe 4th-order range
|
||||
if (k >= kb_s .and. k <= kb_e .and. j >= jb_s .and. j <= jb_e) then
|
||||
|
||||
! set imax and imin 0
|
||||
endif
|
||||
! y direction
|
||||
if(j+2 <= jmax .and. j-2 >= jmin)then
|
||||
|
||||
fy(i,j,k)=d12dy*(fh(i,j-2,k)-EIT*fh(i,j-1,k)+EIT*fh(i,j+1,k)-fh(i,j+2,k))
|
||||
|
||||
elseif(j+1 <= jmax .and. j-1 >= jmin)then
|
||||
|
||||
fy(i,j,k)=d2dy*(-fh(i,j-1,k)+fh(i,j+1,k))
|
||||
|
||||
! set jmax and jmin 0
|
||||
endif
|
||||
! z direction
|
||||
if(k+2 <= kmax .and. k-2 >= kmin)then
|
||||
|
||||
fz(i,j,k)=d12dz*(fh(i,j,k-2)-EIT*fh(i,j,k-1)+EIT*fh(i,j,k+1)-fh(i,j,k+2))
|
||||
|
||||
elseif(k+1 <= kmax .and. k-1 >= kmin)then
|
||||
|
||||
fz(i,j,k)=d2dz*(-fh(i,j,k-1)+fh(i,j,k+1))
|
||||
|
||||
! set kmax and kmin 0
|
||||
endif
|
||||
#elif 0
|
||||
! x direction
|
||||
if(i+2 <= imax .and. i-2 >= imin)then
|
||||
!
|
||||
! f(i-2) - 8 f(i-1) + 8 f(i+1) - f(i+2)
|
||||
! fx(i) = ---------------------------------------------
|
||||
! 12 dx
|
||||
fx(i,j,k)=d12dx*(fh(i-2,j,k)-EIT*fh(i-1,j,k)+EIT*fh(i+1,j,k)-fh(i+2,j,k))
|
||||
|
||||
elseif(i+3 <= imax .and. i-1 >= imin)then
|
||||
fx(i,j,k)=d12dx*(-3.d0*fh(i-1,j,k)-1.d1*fh(i,j,k)+1.8d1*fh(i+1,j,k)-6.d0*fh(i+2,j,k)+fh(i+3,j,k))
|
||||
elseif(i+1 <= imax .and. i-3 >= imin)then
|
||||
fx(i,j,k)=d12dx*( 3.d0*fh(i+1,j,k)+1.d1*fh(i,j,k)-1.8d1*fh(i-1,j,k)+6.d0*fh(i-2,j,k)-fh(i-3,j,k))
|
||||
! set imax and imin 0
|
||||
endif
|
||||
! y direction
|
||||
if(j+2 <= jmax .and. j-2 >= jmin)then
|
||||
|
||||
fy(i,j,k)=d12dy*(fh(i,j-2,k)-EIT*fh(i,j-1,k)+EIT*fh(i,j+1,k)-fh(i,j+2,k))
|
||||
|
||||
elseif(j+3 <= jmax .and. j-1 >= jmin)then
|
||||
fy(i,j,k)=d12dy*(-3.d0*fh(i,j-1,k)-1.d1*fh(i,j,k)+1.8d1*fh(i,j+1,k)-6.d0*fh(i,j+2,k)+fh(i,j+3,k))
|
||||
elseif(j+1 <= jmax .and. j-3 >= jmin)then
|
||||
fy(i,j,k)=d12dy*( 3.d0*fh(i,j+1,k)+1.d1*fh(i,j,k)-1.8d1*fh(i,j-1,k)+6.d0*fh(i,j-2,k)-fh(i,j-3,k))
|
||||
|
||||
! set jmax and jmin 0
|
||||
endif
|
||||
! z direction
|
||||
if(k+2 <= kmax .and. k-2 >= kmin)then
|
||||
|
||||
fz(i,j,k)=d12dz*(fh(i,j,k-2)-EIT*fh(i,j,k-1)+EIT*fh(i,j,k+1)-fh(i,j,k+2))
|
||||
|
||||
elseif(k+3 <= kmax .and. k-1 >= kmin)then
|
||||
fz(i,j,k)=d12dz*(-3.d0*fh(i,j,k-1)-1.d1*fh(i,j,k)+1.8d1*fh(i,j,k+1)-6.d0*fh(i,j,k+2)+fh(i,j,k+3))
|
||||
elseif(k+1 <= kmax .and. k-3 >= kmin)then
|
||||
fz(i,j,k)=d12dz*( 3.d0*fh(i,j,k+1)+1.d1*fh(i,j,k)-1.8d1*fh(i,j,k-1)+6.d0*fh(i,j,k-2)-fh(i,j,k-3))
|
||||
|
||||
! set kmax and kmin 0
|
||||
endif
|
||||
#else
|
||||
! for bam comparison
|
||||
if(i+2 <= imax .and. i-2 >= imin .and. &
|
||||
j+2 <= jmax .and. j-2 >= jmin .and. &
|
||||
k+2 <= kmax .and. k-2 >= kmin) then
|
||||
fx(i,j,k)=d12dx*(fh(i-2,j,k)-EIT*fh(i-1,j,k)+EIT*fh(i+1,j,k)-fh(i+2,j,k))
|
||||
fy(i,j,k)=d12dy*(fh(i,j-2,k)-EIT*fh(i,j-1,k)+EIT*fh(i,j+1,k)-fh(i,j+2,k))
|
||||
fz(i,j,k)=d12dz*(fh(i,j,k-2)-EIT*fh(i,j,k-1)+EIT*fh(i,j,k+1)-fh(i,j,k+2))
|
||||
elseif(i+1 <= imax .and. i-1 >= imin .and. &
|
||||
! 1. Left Boundary Peel
|
||||
do i=1, min(ex(1)-1, ib_s-1)
|
||||
if(i+1 <= imax .and. i-1 >= imin .and. &
|
||||
j+1 <= jmax .and. j-1 >= jmin .and. &
|
||||
k+1 <= kmax .and. k-1 >= kmin) then
|
||||
fx(i,j,k)=d2dx*(-fh(i-1,j,k)+fh(i+1,j,k))
|
||||
fy(i,j,k)=d2dy*(-fh(i,j-1,k)+fh(i,j+1,k))
|
||||
fz(i,j,k)=d2dz*(-fh(i,j,k-1)+fh(i,j,k+1))
|
||||
endif
|
||||
#endif
|
||||
enddo
|
||||
|
||||
! 2. BULK CORE (No branches, full SIMD)
|
||||
!DIR$ SIMD
|
||||
do i=ib_s, ib_e
|
||||
fx(i,j,k)=d12dx*(fh(i-2,j,k)-EIT*fh(i-1,j,k)+EIT*fh(i+1,j,k)-fh(i+2,j,k))
|
||||
fy(i,j,k)=d12dy*(fh(i,j-2,k)-EIT*fh(i,j-1,k)+EIT*fh(i,j+1,k)-fh(i,j+2,k))
|
||||
fz(i,j,k)=d12dz*(fh(i,j,k-2)-EIT*fh(i,j,k-1)+EIT*fh(i,j,k+1)-fh(i,j,k+2))
|
||||
enddo
|
||||
|
||||
! 3. Right Boundary Peel
|
||||
do i=max(1, ib_e+1), ex(1)-1
|
||||
if(i+1 <= imax .and. i-1 >= imin .and. &
|
||||
j+1 <= jmax .and. j-1 >= jmin .and. &
|
||||
k+1 <= kmax .and. k-1 >= kmin) then
|
||||
fx(i,j,k)=d2dx*(-fh(i-1,j,k)+fh(i+1,j,k))
|
||||
fy(i,j,k)=d2dy*(-fh(i,j-1,k)+fh(i,j+1,k))
|
||||
fz(i,j,k)=d2dz*(-fh(i,j,k-1)+fh(i,j,k+1))
|
||||
endif
|
||||
enddo
|
||||
|
||||
else
|
||||
! We are in a boundary slab (j or k is near edge)
|
||||
! Fallback to standard loop with checks (max 2nd order possible here)
|
||||
do i=1,ex(1)-1
|
||||
if(i+1 <= imax .and. i-1 >= imin .and. &
|
||||
j+1 <= jmax .and. j-1 >= jmin .and. &
|
||||
k+1 <= kmax .and. k-1 >= kmin) then
|
||||
fx(i,j,k)=d2dx*(-fh(i-1,j,k)+fh(i+1,j,k))
|
||||
fy(i,j,k)=d2dy*(-fh(i,j-1,k)+fh(i,j+1,k))
|
||||
fz(i,j,k)=d2dz*(-fh(i,j,k-1)+fh(i,j,k+1))
|
||||
endif
|
||||
enddo
|
||||
endif
|
||||
|
||||
enddo
|
||||
enddo
|
||||
|
||||
@@ -2015,8 +1977,12 @@
|
||||
fy = ZEO
|
||||
fz = ZEO
|
||||
|
||||
! Intel compiler directives for aggressive vectorization
|
||||
!DIR$ SIMD
|
||||
!DIR$ IVDEP
|
||||
do k=1,ex(3)-1
|
||||
do j=1,ex(2)-1
|
||||
!DIR$ SIMD
|
||||
do i=1,ex(1)-1
|
||||
! x direction
|
||||
if(i+3 <= imax .and. i-3 >= imin)then
|
||||
@@ -3084,8 +3050,12 @@
|
||||
fy = ZEO
|
||||
fz = ZEO
|
||||
|
||||
! Intel compiler directives for aggressive vectorization
|
||||
!DIR$ SIMD
|
||||
!DIR$ IVDEP
|
||||
do k=1,ex(3)-1
|
||||
do j=1,ex(2)-1
|
||||
!DIR$ SIMD
|
||||
do i=1,ex(1)-1
|
||||
! x direction
|
||||
if(i+4 <= imax .and. i-4 >= imin)then
|
||||
4303
AMSS_NCKU_source/diff_new.f90.backup
Normal file
4303
AMSS_NCKU_source/diff_new.f90.backup
Normal file
File diff suppressed because it is too large
Load Diff
@@ -1513,7 +1513,6 @@
|
||||
real*8,dimension(-1:ex(1),-1:ex(2),-1:ex(3)) :: fh
|
||||
real*8, dimension(3) :: SoA
|
||||
integer :: imin,jmin,kmin,imax,jmax,kmax,i,j,k
|
||||
integer :: i_core_min,i_core_max,j_core_min,j_core_max,k_core_min,k_core_max
|
||||
real*8 :: Sdxdx,Sdydy,Sdzdz,Fdxdx,Fdydy,Fdzdz
|
||||
real*8 :: Sdxdy,Sdxdz,Sdydz,Fdxdy,Fdxdz,Fdydz
|
||||
integer, parameter :: NO_SYMM = 0, EQ_SYMM = 1, OCTANT = 2
|
||||
@@ -1566,47 +1565,9 @@
|
||||
fxz = ZEO
|
||||
fyz = ZEO
|
||||
|
||||
i_core_min = max(1, imin+2)
|
||||
i_core_max = min(ex(1), imax-2)
|
||||
j_core_min = max(1, jmin+2)
|
||||
j_core_max = min(ex(2), jmax-2)
|
||||
k_core_min = max(1, kmin+2)
|
||||
k_core_max = min(ex(3), kmax-2)
|
||||
|
||||
if(i_core_min <= i_core_max .and. j_core_min <= j_core_max .and. k_core_min <= k_core_max)then
|
||||
do k=k_core_min,k_core_max
|
||||
do j=j_core_min,j_core_max
|
||||
do i=i_core_min,i_core_max
|
||||
! interior points always use 4th-order stencils without branch checks
|
||||
fxx(i,j,k) = Fdxdx*(-fh(i-2,j,k)+F16*fh(i-1,j,k)-F30*fh(i,j,k) &
|
||||
-fh(i+2,j,k)+F16*fh(i+1,j,k) )
|
||||
fyy(i,j,k) = Fdydy*(-fh(i,j-2,k)+F16*fh(i,j-1,k)-F30*fh(i,j,k) &
|
||||
-fh(i,j+2,k)+F16*fh(i,j+1,k) )
|
||||
fzz(i,j,k) = Fdzdz*(-fh(i,j,k-2)+F16*fh(i,j,k-1)-F30*fh(i,j,k) &
|
||||
-fh(i,j,k+2)+F16*fh(i,j,k+1) )
|
||||
fxy(i,j,k) = Fdxdy*( (fh(i-2,j-2,k)-F8*fh(i-1,j-2,k)+F8*fh(i+1,j-2,k)-fh(i+2,j-2,k)) &
|
||||
-F8 *(fh(i-2,j-1,k)-F8*fh(i-1,j-1,k)+F8*fh(i+1,j-1,k)-fh(i+2,j-1,k)) &
|
||||
+F8 *(fh(i-2,j+1,k)-F8*fh(i-1,j+1,k)+F8*fh(i+1,j+1,k)-fh(i+2,j+1,k)) &
|
||||
- (fh(i-2,j+2,k)-F8*fh(i-1,j+2,k)+F8*fh(i+1,j+2,k)-fh(i+2,j+2,k)))
|
||||
fxz(i,j,k) = Fdxdz*( (fh(i-2,j,k-2)-F8*fh(i-1,j,k-2)+F8*fh(i+1,j,k-2)-fh(i+2,j,k-2)) &
|
||||
-F8 *(fh(i-2,j,k-1)-F8*fh(i-1,j,k-1)+F8*fh(i+1,j,k-1)-fh(i+2,j,k-1)) &
|
||||
+F8 *(fh(i-2,j,k+1)-F8*fh(i-1,j,k+1)+F8*fh(i+1,j,k+1)-fh(i+2,j,k+1)) &
|
||||
- (fh(i-2,j,k+2)-F8*fh(i-1,j,k+2)+F8*fh(i+1,j,k+2)-fh(i+2,j,k+2)))
|
||||
fyz(i,j,k) = Fdydz*( (fh(i,j-2,k-2)-F8*fh(i,j-1,k-2)+F8*fh(i,j+1,k-2)-fh(i,j+2,k-2)) &
|
||||
-F8 *(fh(i,j-2,k-1)-F8*fh(i,j-1,k-1)+F8*fh(i,j+1,k-1)-fh(i,j+2,k-1)) &
|
||||
+F8 *(fh(i,j-2,k+1)-F8*fh(i,j-1,k+1)+F8*fh(i,j+1,k+1)-fh(i,j+2,k+1)) &
|
||||
- (fh(i,j-2,k+2)-F8*fh(i,j-1,k+2)+F8*fh(i,j+1,k+2)-fh(i,j+2,k+2)))
|
||||
enddo
|
||||
enddo
|
||||
enddo
|
||||
endif
|
||||
|
||||
do k=1,ex(3)
|
||||
do j=1,ex(2)
|
||||
do i=1,ex(1)
|
||||
if(i>=i_core_min .and. i<=i_core_max .and. &
|
||||
j>=j_core_min .and. j<=j_core_max .and. &
|
||||
k>=k_core_min .and. k<=k_core_max) cycle
|
||||
!~~~~~~ fxx
|
||||
if(i+2 <= imax .and. i-2 >= imin)then
|
||||
!
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user