CGH0S7
714c6e90c6
Add !$omp parallel do collapse(2) directives to all triple-loop stencil kernels (fderivs, fdderivs, fdx/fdy/fdz, kodis, lopsided, enforce_ag/enforce_ga) across all ghost_width variants. Add !$omp parallel workshare to RK4/ICN/Euler whole-array update routines. Build system: add -qopenmp to compile and link flags, switch MKL from sequential to threaded (-lmkl_intel_thread -liomp5). Runtime: set OMP_NUM_THREADS=96, OMP_STACKSIZE=16M, OMP_PROC_BIND=close, OMP_PLACES=cores for 96-core server target. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
204 lines
7.8 KiB
Python
Executable File
204 lines
7.8 KiB
Python
Executable File
|
|
##################################################################
|
|
##
|
|
## This file defines the commands used to build and run AMSS-NCKU
|
|
## Author: Xiaoqu
|
|
## 2025/01/24
|
|
##
|
|
##################################################################
|
|
|
|
|
|
import AMSS_NCKU_Input as input_data
|
|
import subprocess
|
|
import time
|
|
import os
|
|
|
|
## OpenMP configuration for threaded Fortran kernels
|
|
## OMP_NUM_THREADS: set to number of physical cores (not hyperthreads)
|
|
## OMP_PROC_BIND: bind threads to cores to avoid migration overhead
|
|
## OMP_STACKSIZE: each thread needs stack space for fh arrays (~3.6MB)
|
|
if "OMP_NUM_THREADS" not in os.environ:
|
|
os.environ["OMP_NUM_THREADS"] = "96"
|
|
os.environ["OMP_STACKSIZE"] = "16M"
|
|
os.environ["OMP_PROC_BIND"] = "close"
|
|
os.environ["OMP_PLACES"] = "cores"
|
|
## CPU core binding configuration using taskset
|
|
## taskset ensures all child processes inherit the CPU affinity mask
|
|
## This forces make and all compiler processes to use only nohz_full cores (4-55, 60-111)
|
|
## Format: taskset -c 4-55,60-111 ensures processes only run on these cores
|
|
#NUMACTL_CPU_BIND = "taskset -c 0-111"
|
|
#NUMACTL_CPU_BIND = "taskset -c 16-47,64-95"
|
|
#NUMACTL_CPU_BIND = "taskset -c 8-15"
|
|
NUMACTL_CPU_BIND = ""
|
|
|
|
## Build parallelism configuration
|
|
## Use nohz_full cores (4-55, 60-111) for compilation: 52 + 52 = 104 cores
|
|
## Set make -j to utilize available cores for faster builds
|
|
BUILD_JOBS = 16
|
|
|
|
|
|
##################################################################
|
|
|
|
|
|
|
|
##################################################################
|
|
|
|
## Compile the AMSS-NCKU main program ABE
|
|
|
|
def makefile_ABE():
|
|
|
|
print( )
|
|
print( " Compiling the AMSS-NCKU executable file ABE/ABEGPU " )
|
|
print( )
|
|
|
|
## Build command with CPU binding to nohz_full cores
|
|
if (input_data.GPU_Calculation == "no"):
|
|
makefile_command = f"{NUMACTL_CPU_BIND} make -j{BUILD_JOBS} ABE"
|
|
elif (input_data.GPU_Calculation == "yes"):
|
|
makefile_command = f"{NUMACTL_CPU_BIND} make -j{BUILD_JOBS} ABEGPU"
|
|
else:
|
|
print( " CPU/GPU numerical calculation setting is wrong " )
|
|
print( )
|
|
|
|
## Execute the command with subprocess.Popen and stream output
|
|
makefile_process = subprocess.Popen(makefile_command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True)
|
|
|
|
## Read and print output lines as they arrive
|
|
for line in makefile_process.stdout:
|
|
print(line, end='') # stream output in real time
|
|
|
|
## Wait for the process to finish
|
|
makefile_return_code = makefile_process.wait()
|
|
if makefile_return_code != 0:
|
|
raise subprocess.CalledProcessError(makefile_return_code, makefile_command)
|
|
|
|
print( )
|
|
print( " Compilation of the AMSS-NCKU executable file ABE is finished " )
|
|
print( )
|
|
|
|
return
|
|
|
|
##################################################################
|
|
|
|
|
|
|
|
##################################################################
|
|
|
|
## Compile the AMSS-NCKU TwoPuncture program TwoPunctureABE
|
|
|
|
def makefile_TwoPunctureABE():
|
|
|
|
print( )
|
|
print( " Compiling the AMSS-NCKU executable file TwoPunctureABE " )
|
|
print( )
|
|
|
|
## Build command with CPU binding to nohz_full cores
|
|
makefile_command = f"{NUMACTL_CPU_BIND} make -j{BUILD_JOBS} TwoPunctureABE"
|
|
|
|
## Execute the command with subprocess.Popen and stream output
|
|
makefile_process = subprocess.Popen(makefile_command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True)
|
|
|
|
## Read and print output lines as they arrive
|
|
for line in makefile_process.stdout:
|
|
print(line, end='') # stream output in real time
|
|
|
|
## Wait for the process to finish
|
|
makefile_return_code = makefile_process.wait()
|
|
if makefile_return_code != 0:
|
|
raise subprocess.CalledProcessError(makefile_return_code, makefile_command)
|
|
|
|
print( )
|
|
print( " Compilation of the AMSS-NCKU executable file TwoPunctureABE is finished " )
|
|
print( )
|
|
|
|
return
|
|
|
|
##################################################################
|
|
|
|
|
|
|
|
##################################################################
|
|
|
|
## Run the AMSS-NCKU main program ABE
|
|
|
|
def run_ABE():
|
|
|
|
print( )
|
|
print( " Running the AMSS-NCKU executable file ABE/ABEGPU " )
|
|
print( )
|
|
|
|
## Define the command to run; cast other values to strings as needed
|
|
|
|
if (input_data.GPU_Calculation == "no"):
|
|
run_command = NUMACTL_CPU_BIND + " ./ABE"
|
|
run_command_outfile = "ABE_out.log"
|
|
elif (input_data.GPU_Calculation == "yes"):
|
|
run_command = NUMACTL_CPU_BIND + " ./ABEGPU"
|
|
run_command_outfile = "ABEGPU_out.log"
|
|
|
|
## Execute the command and stream output
|
|
run_process = subprocess.Popen(run_command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True)
|
|
|
|
## Write ABE run output to file while printing to stdout
|
|
with open(run_command_outfile, 'w') as file0:
|
|
## Read and print output lines; also write each line to file
|
|
for line in run_process.stdout:
|
|
print(line, end='') # stream output in real time
|
|
file0.write(line) # write the line to file
|
|
file0.flush() # flush to ensure each line is written immediately (optional)
|
|
file0.close()
|
|
|
|
## Wait for the process to finish
|
|
run_return_code = run_process.wait()
|
|
|
|
print( )
|
|
print( " The ABE/ABEGPU simulation is finished " )
|
|
print( )
|
|
|
|
return
|
|
|
|
##################################################################
|
|
|
|
|
|
|
|
##################################################################
|
|
|
|
## Run the AMSS-NCKU TwoPuncture program TwoPunctureABE
|
|
|
|
def run_TwoPunctureABE():
|
|
tp_time1=time.time()
|
|
print( )
|
|
print( " Running the AMSS-NCKU executable file TwoPunctureABE " )
|
|
print( )
|
|
|
|
## Define the command to run
|
|
#TwoPuncture_command = NUMACTL_CPU_BIND + " ./TwoPunctureABE"
|
|
TwoPuncture_command = " ./TwoPunctureABE"
|
|
TwoPuncture_command_outfile = "TwoPunctureABE_out.log"
|
|
|
|
## Execute the command with subprocess.Popen and stream output
|
|
TwoPuncture_process = subprocess.Popen(TwoPuncture_command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True)
|
|
|
|
## Write TwoPunctureABE run output to file while printing to stdout
|
|
with open(TwoPuncture_command_outfile, 'w') as file0:
|
|
## Read and print output lines; also write each line to file
|
|
for line in TwoPuncture_process.stdout:
|
|
print(line, end='') # stream output in real time
|
|
file0.write(line) # write the line to file
|
|
file0.flush() # flush to ensure each line is written immediately (optional)
|
|
file0.close()
|
|
|
|
## Wait for the process to finish
|
|
TwoPuncture_command_return_code = TwoPuncture_process.wait()
|
|
|
|
print( )
|
|
print( " The TwoPunctureABE simulation is finished " )
|
|
print( )
|
|
tp_time2=time.time()
|
|
et=tp_time2-tp_time1
|
|
print(f"Used time: {et}")
|
|
return
|
|
|
|
##################################################################
|
|
|