278 lines
10 KiB
Python
Executable File
278 lines
10 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 os
|
|
import subprocess
|
|
import time
|
|
|
|
|
|
def get_last_n_cores_per_socket(n=32):
|
|
"""
|
|
Read CPU topology via lscpu and return a taskset -c string
|
|
selecting the last `n` cores of each NUMA node (socket).
|
|
|
|
Example: 2 sockets x 56 cores each, n=32 -> node0: 24-55, node1: 80-111
|
|
-> "taskset -c 24-55,80-111"
|
|
"""
|
|
result = subprocess.run(["lscpu", "--parse=NODE,CPU"], capture_output=True, text=True)
|
|
|
|
# Build a dict: node_id -> sorted list of CPU ids
|
|
node_cpus = {}
|
|
for line in result.stdout.splitlines():
|
|
if line.startswith("#") or not line.strip():
|
|
continue
|
|
parts = line.split(",")
|
|
if len(parts) < 2:
|
|
continue
|
|
node_id, cpu_id = int(parts[0]), int(parts[1])
|
|
node_cpus.setdefault(node_id, []).append(cpu_id)
|
|
|
|
segments = []
|
|
for node_id in sorted(node_cpus):
|
|
cpus = sorted(node_cpus[node_id])
|
|
selected = cpus[-n:] # last n cores of this socket
|
|
segments.append(f"{selected[0]}-{selected[-1]}")
|
|
|
|
cpu_str = ",".join(segments)
|
|
total = len(segments) * n
|
|
print(f" CPU binding: taskset -c {cpu_str} ({total} cores, last {n} per socket)")
|
|
#return f"taskset -c {cpu_str}"
|
|
return f""
|
|
|
|
|
|
## CPU core binding: dynamically select the last 32 cores of each socket (64 cores total)
|
|
NUMACTL_CPU_BIND = get_last_n_cores_per_socket(n=32)
|
|
|
|
## Build parallelism: match the number of bound cores
|
|
BUILD_JOBS = 64
|
|
|
|
|
|
##################################################################
|
|
|
|
|
|
##################################################################
|
|
|
|
def prepare_gpu_runtime_env():
|
|
"""
|
|
Create a user-private CUDA MPS environment for GPU runs.
|
|
|
|
On shared machines another user's daemon may already occupy the default
|
|
/tmp/nvidia-mps pipe directory, which makes plain cudaSetDevice/cudaMalloc
|
|
fail with cudaErrorMpsConnectionFailed. Binding AMSS-NCKU to a private
|
|
pipe directory avoids cross-user interference.
|
|
"""
|
|
env = os.environ.copy()
|
|
|
|
pipe_dir = env.get("CUDA_MPS_PIPE_DIRECTORY", f"/tmp/amss-ncku-mps-{os.getuid()}")
|
|
log_dir = env.get("CUDA_MPS_LOG_DIRECTORY", f"/tmp/amss-ncku-mps-log-{os.getuid()}")
|
|
|
|
os.makedirs(pipe_dir, exist_ok=True)
|
|
os.makedirs(log_dir, exist_ok=True)
|
|
|
|
env["CUDA_MPS_PIPE_DIRECTORY"] = pipe_dir
|
|
env["CUDA_MPS_LOG_DIRECTORY"] = log_dir
|
|
|
|
control_socket = os.path.join(pipe_dir, "control")
|
|
if not os.path.exists(control_socket):
|
|
start = subprocess.run(
|
|
["nvidia-cuda-mps-control", "-d"],
|
|
env=env,
|
|
stdout=subprocess.DEVNULL,
|
|
stderr=subprocess.DEVNULL,
|
|
)
|
|
if start.returncode != 0:
|
|
print(f" Warning: failed to start private CUDA MPS daemon in {pipe_dir}")
|
|
else:
|
|
print(f" Using private CUDA MPS pipe directory: {pipe_dir}")
|
|
else:
|
|
print(f" Using existing private CUDA MPS pipe directory: {pipe_dir}")
|
|
|
|
return env
|
|
|
|
##################################################################
|
|
|
|
|
|
|
|
##################################################################
|
|
|
|
## 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} INTERP_LB_MODE=off 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
|
|
|
|
run_env = None
|
|
|
|
if (input_data.GPU_Calculation == "no"):
|
|
mpi_command = NUMACTL_CPU_BIND + " mpirun -np " + str(input_data.MPI_processes) + " ./ABE"
|
|
#mpi_command = " mpirun -np " + str(input_data.MPI_processes) + " ./ABE"
|
|
mpi_command_outfile = "ABE_out.log"
|
|
elif (input_data.GPU_Calculation == "yes"):
|
|
run_env = prepare_gpu_runtime_env()
|
|
if int(input_data.MPI_processes) == 1:
|
|
mpi_command = "./ABEGPU"
|
|
else:
|
|
mpi_command = NUMACTL_CPU_BIND + " mpirun -np " + str(input_data.MPI_processes) + " ./ABEGPU"
|
|
mpi_command_outfile = "ABEGPU_out.log"
|
|
|
|
## Execute the MPI command and stream output
|
|
mpi_process = subprocess.Popen(
|
|
mpi_command,
|
|
shell=True,
|
|
stdout=subprocess.PIPE,
|
|
stderr=subprocess.STDOUT,
|
|
text=True,
|
|
env=run_env,
|
|
)
|
|
|
|
## Write ABE run output to file while printing to stdout
|
|
with open(mpi_command_outfile, 'w') as file0:
|
|
## Read and print output lines; also write each line to file
|
|
for line in mpi_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
|
|
mpi_return_code = mpi_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
|
|
|
|
##################################################################
|
|
|