def get_pipeline(shared_fs=False, size=1):
p = Pipeline()
p.name = 'p'
n = 4
s1 = Stage()
s1.name = 's1'
for x in range(n):
t = Task()
t.name = 't%s'%x
# dd if=/dev/random bs=<byte size of a chunk> count=<number of chunks> of=<output file name>
t.executable = 'dd'
if not shared_fs:
t.arguments = ['if=/dev/urandom','bs=%sM'%size, 'count=1', 'of=$NODE_LFS_PATH/s1_t%s.txt'%x]
else:
t.arguments = ['if=/dev/urandom','bs=%sM'%size, 'count=1', 'of=/home/vivek91/s1_t%s.txt'%x]
t.cpu_reqs['processes'] = 1
t.cpu_reqs['threads_per_process'] = 24
t.cpu_reqs['thread_type'] = ''
t.cpu_reqs['process_type'] = ''
t.lfs_per_process = 1024
s1.add_tasks(t)
p.add_stages(s1)
s2 = Stage()
s2.name = 's2'
for x in range(n):
t = Task()
t.executable = ['dd']
if not shared_fs:
t.arguments = ['if=$NODE_LFS_PATH/s1_t%s.txt'%x,'bs=%sM'%size, 'count=1', 'of=$NODE_LFS_PATH/s2_t%s.txt'%x]
else:
t.arguments = ['if=/home/vivek91/s1_t%s.txt'%x,'bs=%sM'%size, 'count=1', 'of=/home/vivek91/s2_t%s.txt'%x]
t.cpu_reqs['processes'] = 1
t.cpu_reqs['threads_per_process'] = 24
t.cpu_reqs['thread_type'] = ''
t.cpu_reqs['process_type'] = ''
t.tag = 't%s'%x
s2.add_tasks(t)
p.add_stages(s2)
return p
def generate_pipeline(name, stages):
# Create a Pipeline object
p = Pipeline()
p.name = name
for s_cnt in range(stages):
# Create a Stage object
s = Stage()
s.name = 'Stage %s'%s_cnt
for t_cnt in range(5):
# Create a Task object
t = Task()
t.name = 'my-task' # Assign a name to the task (optional)
t.executable = '/bin/echo' # Assign executable to the task
# Assign arguments for the task executable
t.arguments = ['I am task %s in %s in %s'%(t_cnt, s_cnt, name)]
# Add the Task to the Stage
s.add_tasks(t)
# Add Stage to the Pipeline
p.add_stages(s)
return p
def test_stage_post_exec():
global p1
p1.name = 'p1'
s = Stage()
s.name = 's1'
for t in range(NUM_TASKS):
s.add_tasks(create_single_task())
s.post_exec = condition
p1.add_stages(s)
res_dict = {
'resource': 'local.localhost',
'walltime': 30,
'cpus': 1,
}
os.environ['RADICAL_PILOT_DBURL'] = MLAB
appman = AppManager(rts='radical.pilot', hostname=hostname, port=port)
appman.resource_desc = res_dict
appman.workflow = [p1]
appman.run()
def test_state_order():
"""
**Purpose**: Test if the Pipeline, Stage and Task are assigned their states in the correct order
"""
def create_single_task():
t1 = Task()
t1.name = 'simulation'
t1.executable = ['/bin/date']
t1.copy_input_data = []
t1.copy_output_data = []
return t1
p1 = Pipeline()
p1.name = 'p1'
s = Stage()
s.name = 's1'
s.tasks = create_single_task()
s.add_tasks(create_single_task())
p1.add_stages(s)
res_dict = {
'resource': 'local.localhost',
'walltime': 5,
'cpus': 1,
'project': ''
}
os.environ['RADICAL_PILOT_DBURL'] = MLAB
os.environ['RP_ENABLE_OLD_DEFINES'] = 'True'
appman = Amgr(hostname=hostname, port=port)
appman.resource_desc = res_dict
appman.workflow = [p1]
appman.run()
p_state_hist = p1.state_history
assert p_state_hist == ['DESCRIBED', 'SCHEDULING', 'DONE']
s_state_hist = p1.stages[0].state_history
assert s_state_hist == ['DESCRIBED', 'SCHEDULING', 'SCHEDULED', 'DONE']
tasks = p1.stages[0].tasks
for t in tasks:
t_state_hist = t.state_history
assert t_state_hist == ['DESCRIBED', 'SCHEDULING', 'SCHEDULED', 'SUBMITTING', 'SUBMITTED',
'EXECUTED', 'DEQUEUEING', 'DEQUEUED', 'DONE']
def write_sources(cmt_file_db, param_path, task_counter):
""" This function creates a stage that modifies the CMTSOLUTION files
before the simulations are run.
:param cmt_file_db: cmtfile in the database
:param param_path: path to parameter file directory
:param task_counter: total task count up until now in pipeline
:return: EnTK Stage
"""
# Get Database parameters
databaseparam_path = os.path.join(param_path,
"Database/DatabaseParameters.yml")
DB_params = read_yaml_file(databaseparam_path)
# Earthquake specific database parameters: Dir and Cid
Cdir, Cid = get_Centry_path(DB_params["databasedir"], cmt_file_db)
# Path to function
write_source_func = os.path.join(bin_path, "write_sources.py")
# Create a Stage object
w_sources = Stage()
w_sources.name = "Write-Sources"
# Create Task for stage
w_sources_t = Task()
w_sources_t.name = "Task-Sources"
w_sources_t.pre_exec = [ # Conda activate
DB_params["conda-activate"]
]
w_sources_t.executable = DB_params["bin-python"] #
# Assign executable
# to the task
w_sources_t.arguments = [write_source_func, cmt_file_db]
# In the future maybe to database dir as a total log?
w_sources_t.stdout = os.path.join(
"%s" % Cdir, "logs", "stdout.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), w_sources_t.name))
w_sources_t.stderr = os.path.join(
"%s" % Cdir, "logs", "stderr.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), w_sources_t.name))
# Add Task to the Stage
w_sources.add_tasks(w_sources_t)
task_counter += 1
return w_sources, task_counter
def create_process_path_files(cmt_file_db, param_path, task_counter):
"""This function creates the path files used for processing both
synthetic and observed data in ASDF format, as well as the following
windowing procedure.
:param cmt_file_db: cmtfile in the database
:param param_path: path to parameter file directory
:param pipelinedir: path to pipeline directory
:return: EnTK Stage
"""
# Get database parameter path
databaseparam_path = os.path.join(param_path,
"Database/DatabaseParameters.yml")
# Load Parameters
DB_params = read_yaml_file(databaseparam_path)
# Earthquake specific database parameters: Dir and Cid
Cdir, Cid = get_Centry_path(DB_params["databasedir"], cmt_file_db)
# Process path function
create_process_path_bin = os.path.join(bin_path, "create_path_files.py")
# Create Process Paths Stage (CPP)
# Create a Stage object
cpp = Stage()
cpp.name = "CreateProcessPaths"
# Create Task
cpp_t = Task()
cpp_t.name = "CPP-Task"
cpp_t.pre_exec = [ # Conda activate
DB_params["conda-activate"]
]
cpp_t.executable = DB_params["bin-python"] # Assign executable
# to the task
cpp_t.arguments = [create_process_path_bin, cmt_file_db]
# In the future maybe to database dir as a total log?
cpp_t.stdout = os.path.join(
"%s" % Cdir, "logs", "stdout.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), cpp_t.name))
cpp_t.stderr = os.path.join(
"%s" % Cdir, "logs", "stderr.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), cpp_t.name))
task_counter += 1
cpp.add_tasks(cpp_t)
return cpp, task_counter
def _generate_stage(self, stage_type):
"""
Parameters
----------
stage_type : str
key into self.stages dictionary to retrieve stage name and taskmanagers.
"""
stage = Stage()
stage.name = self.stages[stage_type].name
for taskman in self.stages[stage_type].taskmanagers:
stage.add_tasks(set(taskman.tasks(self.current_iter)))
return stage
def generate_interfacing_stage():
s4 = Stage()
s4.name = 'scanning'
# Scaning for outliers and prepare the next stage of MDs
t4 = Task()
t4.pre_exec = []
#t4.pre_exec += ['. /sw/summit/python/2.7/anaconda2/5.3.0/etc/profile.d/conda.sh']
#t4.pre_exec += ['module load cuda/9.1.85']
#t4.pre_exec += ['conda activate %s' % conda_path]
t4.pre_exec += [
'module unload prrte', 'module unload python', 'module load xl',
'module load xalt', 'module load spectrum-mpi', 'module load cuda',
'module list'
]
t4.pre_exec += [
'. /sw/summit/ibm-wml-ce/anaconda-base/etc/profile.d/conda.sh',
'source /sw/summit/ibm-wml-ce/anaconda-base/etc/profile.d/conda.sh',
'conda deactivate', 'conda deactivate',
'conda activate /gpfs/alpine/proj-shared/med110/wf-2/conda/envs/ibm-wml-ce-cloned'
]
#'conda activate /sw/summit/ibm-wml-ce/anaconda-base/envs/ibm-wml-ce-1.7.0-2']
t4.pre_exec += [
'export PYTHONPATH=%s/CVAE_exps:%s/CVAE_exps/cvae:$PYTHONPATH' %
(base_path, base_path)
]
t4.pre_exec += ['cd %s/Outlier_search' % base_path]
#t4.executable = ['%s/bin/python' % conda_path]
t4.executable = ['python']
t4.arguments = [
'outlier_locator.py', '--md', md_path, '--cvae', cvae_path,
'--pdb', pdb_file
]
#'--ref', ref_pdb_file]
t4.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 16,
'thread_type': 'OpenMP'
}
t4.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': 'CUDA'
}
s4.add_tasks(t4)
s4.post_exec = func_condition
return s4
def generate_pipeline(nid):
p = Pipeline()
p.name = 'p%s' % nid
s1 = Stage()
s1.name = 's1'
t1 = Task()
t1.name = 't2'
t1.executable = '/bin/echo'
t1.arguments = ['hello']
s1.add_tasks(t1)
p.add_stages(s1)
s2 = Stage()
s2.name = 's2'
s2_task_uids = []
for cnt in range(10):
t2 = Task()
t2.name = 't%s' % (cnt + 1)
t2.executable = '/bin/echo'
t2.arguments = ['world']
# Copy data from the task in first stage to the current task's location
t2.copy_input_data = [
'$Pipeline_%s_Stage_%s_Task_%s/output.txt' %
(p.name, s1.name, t1.name)
]
s2.add_tasks(t2)
s2_task_uids.append(t2.name)
p.add_stages(s2)
return p
def generate_interfacing_stage():
s4 = Stage()
s4.name = 'scanning'
# Scaning for outliers and prepare the next stage of MDs
t4 = Task()
t4.pre_exec = []
t4.pre_exec = ['module reset']
t4.pre_exec += [
'. /sw/summit/python/2.7/anaconda2/5.3.0/etc/profile.d/conda.sh'
]
t4.pre_exec += ['module load cuda/9.1.85']
t4.pre_exec += ['conda activate rp.copy']
t4.pre_exec += ['export CUDA_VISIBLE_DEVICES=0']
t4.pre_exec += [
'export PYTHONPATH=/gpfs/alpine/bip179/scratch/hrlee/hyperspace/microscope/experiments/CVAE_exps:$PYTHONPATH'
]
t4.pre_exec += [
'cd /gpfs/alpine/bip179/scratch/hrlee/hyperspace/microscope/experiments/Outlier_search'
]
# python outlier_locator.py -m ../MD_exps/fs-pep -c ../CVAE_exps -p ../MD_exps/fs-pep/pdb/100-fs-peptide-400K.pdb
t4.executable = ['/ccs/home/hrlee/.conda/envs/rp.copy/bin/python']
t4.arguments = [
'outlier_locator.py', '--md', '../MD_exps/fs-pep', '--cvae',
'../CVAE_exps --pdb',
'../MD_exps/fs-pep/pdb/100-fs-peptide-400K.pdb'
]
# t4.arguments = ['/gpfs/alpine/bip179/scratch/hrlee/hyperspace/microscope/experiments/Outlier_search/outlier_locator.py',
# '-m', '/gpfs/alpine/bip179/scratch/hrlee/hyperspace/microscope/experiments/MD_exps/fs-pep',
# '-c', '/gpfs/alpine/bip179/scratch/hrlee/hyperspace/microscope/experiments/CVAE_exps',
# '-p', '/gpfs/alpine/bip179/scratch/hrlee/hyperspace/microscope/experiments/MD_exps/fs-pep/pdb/100-fs-peptide-400K.pdb'
# ]
t4.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 12,
'thread_type': 'OpenMP'
}
t4.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': 'CUDA'
}
s4.add_tasks(t4)
s4.post_exec = func_condition
return s4
def specfem_clean_up(cmt_file_db, param_path, task_counter):
""" Cleaning up the simulation directories since we don"t need all the
files for the future.
:param cmt_file_db: cmtfile in the database
:param param_path: path to parameter file directory
:param pipelinedir: path to pipeline directory
:return: EnTK Stage
"""
# Get Database parameters
databaseparam_path = os.path.join(param_path,
"Database/DatabaseParameters.yml")
# Database parameters.
DB_params = read_yaml_file(databaseparam_path)
# Earthquake specific database parameters: Dir and Cid
Cdir, Cid = get_Centry_path(DB_params["databasedir"], cmt_file_db)
# Path to function
clean_up_func = os.path.join(bin_path, "clean_up_simdirs.py")
# Create a Stage object
clean_up = Stage()
clean_up.name = "Clean-Up"
# Create Task for stage
clean_up_t = Task()
clean_up_t.name = "Task-Clean-Up"
clean_up_t.pre_exec = [ # Conda activate
DB_params["conda-activate"]
]
clean_up_t.executable = DB_params["bin-python"] # Assign executable
# to the task
clean_up_t.arguments = [clean_up_func, cmt_file_db]
# In the future maybe to database dir as a total log?
clean_up_t.stdout = os.path.join(
"%s" % Cdir, "logs", "stdout.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), clean_up_t.name))
clean_up_t.stderr = os.path.join(
"%s" % Cdir, "logs", "stderr.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), clean_up_t.name))
# Add Task to the Stage
clean_up.add_tasks(clean_up_t)
return clean_up, task_counter
def generate_MD_stage(num_MD=1):
"""
Function to generate MD stage.
"""
s1 = Stage()
s1.name = 'MD'
# MD tasks
time_stamp = int(time.time())
for i in range(num_MD):
t1 = Task()
t1.pre_exec = [
'. /sw/summit/python/2.7/anaconda2/5.3.0/etc/profile.d/conda.sh'
]
t1.pre_exec += ['module load cuda/9.1.85']
t1.pre_exec += ['conda activate %s' % conda_path]
t1.pre_exec += [
'export PYTHONPATH=%s/MD_exps:$PYTHONPATH' % base_path
]
t1.pre_exec += ['cd %s/MD_exps/fs-pep' % base_path]
t1.pre_exec += [
'mkdir -p omm_runs_%d && cd omm_runs_%d' %
(time_stamp + i, time_stamp + i)
]
t1.executable = ['%s/bin/python' % conda_path] # run_openmm.py
t1.arguments = ['%s/MD_exps/fs-pep/run_openmm.py' % base_path]
# t1.arguments += ['--topol', '%s/MD_exps/fs-pep/pdb/topol.top' % base_path]
t1.arguments += [
'--pdb_file',
'%s/MD_exps/fs-pep/pdb/100-fs-peptide-400K.pdb' % base_path,
'--length', LEN_sim
]
# assign hardware the task
t1.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 4,
'thread_type': 'OpenMP'
}
t1.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': 'CUDA'
}
# Add the MD task to the simulating stage
s1.add_tasks(t1)
return s1
def generate_interfacing_stage():
s4 = Stage()
s4.name = 'scanning'
# Scaning for outliers and prepare the next stage of MDs
t4 = Task()
t4.pre_exec = ['. /sw/summit/python/3.6/anaconda3/5.3.0/etc/profile.d/conda.sh']
t4.pre_exec += ['conda activate %s' % cfg['conda_pytorch']]
t4.pre_exec += ['mkdir -p %s/Outlier_search/outlier_pdbs' % cfg['base_path']]
t4.pre_exec += ['export models=""; for i in `ls -d %s/CVAE_exps/model-cvae_runs*/`; do if [ "$models" != "" ]; then models=$models","$i; else models=$i; fi; done;cat /dev/null' % cfg['base_path']]
t4.pre_exec += ['export LANG=en_US.utf-8', 'export LC_ALL=en_US.utf-8']
t4.pre_exec += ['unset CUDA_VISIBLE_DEVICES', 'export OMP_NUM_THREADS=4']
cmd_cat = 'cat /dev/null'
cmd_jsrun = 'jsrun -n %s -a 6 -g 6 -r 1 -c 7' % cfg['node_counts']
#molecules_path = '/gpfs/alpine/world-shared/ven201/tkurth/molecules/'
t4.executable = [' %s; %s %s/examples/outlier_detection/run_optics_dist_summit_entk.sh' % (cmd_cat, cmd_jsrun, cfg['molecules_path'])]
t4.arguments = ['%s/bin/python' % cfg['conda_pytorch']]
t4.arguments += ['%s/examples/outlier_detection/optics.py' % cfg['molecules_path'],
'--sim_path', '%s/MD_exps/%s' % (cfg['base_path'], cfg['system_name']),
'--pdb_out_path', '%s/Outlier_search/outlier_pdbs' % cfg['base_path'],
'--restart_points_path',
'%s/Outlier_search/restart_points.json' % cfg['base_path'],
'--data_path', '%s/MD_to_CVAE/cvae_input.h5' % cfg['base_path'],
'--model_paths', '$models',
'--model_type', cfg['model_type'],
'--min_samples', 10,
'--n_outliers', 500,
'--dim1', cfg['residues'],
'--dim2', cfg['residues'],
'--cm_format', 'sparse-concat',
'--batch_size', cfg['batch_size'],
'--distributed',
'-iw', cfg['init_weights']]
t4.cpu_reqs = {'processes' : 1,
'process_type' : None,
'threads_per_process': 12,
'thread_type' : 'OpenMP'}
t4.gpu_reqs = {'processes' : 1,
'process_type' : None,
'threads_per_process': 1,
'thread_type' : 'CUDA'}
s4.add_tasks(t4)
s4.post_exec = func_condition
return s4
def generate_ML_stage(num_ML=1):
"""
Function to generate the learning stage
"""
s3 = Stage()
s3.name = 'learning'
# learn task
time_stamp = int(time.time())
for i in range(num_ML):
t3 = Task()
# https://github.com/radical-collaboration/hyperspace/blob/MD/microscope/experiments/CVAE_exps/train_cvae.py
t3.pre_exec = []
t3.pre_exec += [
'. /sw/summit/python/2.7/anaconda2/5.3.0/etc/profile.d/conda.sh'
]
t3.pre_exec += ['module load cuda/9.1.85']
t3.pre_exec += ['conda activate %s' % conda_path]
t3.pre_exec += [
'export PYTHONPATH=%s/CVAE_exps:$PYTHONPATH' % base_path
]
t3.pre_exec += ['cd %s' % cvae_path]
dim = i + 3
cvae_dir = 'cvae_runs_%.2d_%d' % (dim, time_stamp + i)
t3.pre_exec += ['mkdir -p {0} && cd {0}'.format(cvae_dir)]
t3.executable = ['%s/bin/python' % conda_path] # train_cvae.py
t3.arguments = [
'%s/train_cvae.py' % cvae_path, '--h5_file',
'%s/cvae_input.h5' % agg_path, '--dim', dim
]
t3.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 4,
'thread_type': 'OpenMP'
}
t3.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': 'CUDA'
}
# Add the learn task to the learning stage
s3.add_tasks(t3)
return s3
def esmacs(cfg, names, stage, outdir):
s = Stage()
s.name = 'S3.%s' % stage
#print("DEBUG:instantiation: %s" % len(s._tasks))
for comp in names:
#print("DEBUG:first loop: %s" % len(s._tasks))
for i in range(1, cfg['n_replicas']):
#print("DEBUG:second loop:start: %s" % len(s._tasks))
t = Task()
# RCT native
t.pre_exec = [
#". /sw/summit/lmod/lmod/init/profile",
"export WDIR=\"{}\"".format(comp),
". {}".format(cfg['conda_init']),
"conda activate {}".format(cfg['conda_esmacs_task_env']),
"module load {}".format(cfg['esmacs_task_modules']),
"mkdir -p $WDIR/replicas/rep{}/{}".format(i, outdir),
"cd $WDIR/replicas/rep{}/{}".format(i, outdir),
#"rm -f {}.log {}.xml {}.dcd {}.chk".format(stage, stage, stage, stage),
"export OMP_NUM_THREADS=1"]
t.executable = 'python3'
t.arguments = ['$WDIR/{}.py'.format(stage)]
# Bash wrapper
#t.executable = '%s/wf3.sh' % comp
#t.arguments = [comp, i, outdir, stage,
# cfg['conda_init'],
# cfg['conda_esmacs_task_env'],
# cfg['esmacs_task_modules']]
t.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 4,
'thread_type': 'OpenMP'}
t.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': 'CUDA'}
s.add_tasks(t)
#print("DEBUG:second loop:end: %s" % len(s._tasks))
return s
def on_true():
nonlocal NUM_TASKS, CUR_STAGE, p1
NUM_TASKS *= 2
s = Stage()
s.name = 's%s' % CUR_STAGE
for _ in range(NUM_TASKS):
s.add_tasks(create_single_task())
s.post_exec = condition
p1.add_stages(s)
def on_true():
global NUM_TASKS, CUR_STAGE
NUM_TASKS *= 2
s = Stage()
s.name = 's%s'%CUR_STAGE
for t in range(NUM_TASKS):
s.add_tasks(create_single_task())
s.post_exec = condition
p1.add_stages(s)
def describe_MD_pipeline():
p = Pipeline()
p.name = 'MD'
# MD stage
s1 = Stage()
s1.name = 'OpenMM'
# Each Task() is an OpenMM executable that will run on a single GPU.
# Set sleep time for local testing
# for i in range(18):
task = Task()
task.name = 'md'
task.pre_exec = []
# task.pre_exec += ['export MINICONDA=/gpfs/alpine/scratch/jdakka/bip178/miniconda']
# task.pre_exec += ['export PATH=$MINICONDA/bin:$PATH']
# task.pre_exec += ['export LD_LIBRARY_PATH=$MINICONDA/lib:$LD_LIBRARY_PATH']
task.pre_exec += ['module load python/2.7.15-anaconda2-5.3.0']
task.pre_exec += ['module load cuda/9.1.85']
task.pre_exec += ['module load gcc/6.4.0']
task.pre_exec += ['source activate openmm']
task.pre_exec += ['cd /gpfs/alpine/scratch/jdakka/bip178/benchmarks/MD_exps/fs-pep/results_2']
task.executable = '/ccs/home/jdakka/.conda/envs/openmm/bin/python'
task.arguments = ['run_openmm.py', '-f',
'/gpfs/alpine/scratch/jdakka/bip178/benchmarks/MD_exps/fs-pep/pdb/100-fs-peptide-400K.pdb']
task.cpu_reqs = {'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': None
}
task.gpu_reqs = {'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': 'CUDA'
}
# Add the MD task to the Docking Stage
s1.add_tasks(task)
# Add MD stage to the MD Pipeline
p.add_stages(s1)
return p
def test_state_order():
"""
**Purpose**: Test if the Pipeline, Stage and Task are assigned their states
in the correct order
"""
def create_single_task():
t1 = Task()
t1.name = 'simulation'
t1.executable = '/bin/date'
t1.copy_input_data = []
t1.copy_output_data = []
return t1
p1 = Pipeline()
p1.name = 'p1'
s = Stage()
s.name = 's1'
s.tasks = create_single_task()
s.add_tasks(create_single_task())
p1.add_stages(s)
res_dict = {'resource': 'local.localhost',
'walltime': 5,
'cpus' : 1,
'project' : ''}
os.environ['RP_ENABLE_OLD_DEFINES'] = 'True'
appman = Amgr(hostname=host, port=port)
appman.resource_desc = res_dict
appman.workflow = [p1]
appman.run()
p_state_hist = p1.state_history
assert p_state_hist == ['DESCRIBED', 'SCHEDULING', 'DONE']
s_state_hist = p1.stages[0].state_history
assert s_state_hist == ['DESCRIBED', 'SCHEDULING', 'SCHEDULED', 'DONE']
for t in p1.stages[0].tasks:
assert t.state_history == ['DESCRIBED', 'SCHEDULING', 'SCHEDULED',
'SUBMITTING', 'EXECUTED', 'DONE']
def generate_ML_tasks(self):
"""
Function to generate the learning stage
"""
p = Pipeline()
p.name = 'learning'
s3 = Stage()
s3.name = 'training'
# learn task
for i in range(self.num_ML):
t3 = Task()
# https://github.com/radical-collaboration/hyperspace/blob/MD/microscope/experiments/CVAE_exps/train_cvae.py
t3.pre_exec = []
t3.pre_exec += ['. /sw/summit/python/2.7/anaconda2/5.3.0/etc/profile.d/conda.sh']
t3.pre_exec += ['module load cuda/10.1.168']
t3.pre_exec += ['conda activate %s' % conda_path]
t3.pre_exec += ['export PYTHONPATH=%s/CVAE_exps:$PYTHONPATH' % base_path]
t3.pre_exec += ['cd %s' % cvae_path]
t3.pre_exec += [f"sleep {i}"]
dim = i + 3
t3.executable = ['%s/bin/python' % conda_path] # train_cvae.py
t3.arguments = [
'%s/train_cvae.py' % cvae_path,
'--h5_file', '%s/cvae_input.h5' % agg_path,
'--dim', dim]
t3.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 4,
'thread_type': 'OpenMP'
}
t3.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': 'CUDA'
}
# Add the learn task to the learning stage
s3.add_tasks(t3)
p.add_stages(s3)
return p
def generate_ML_pipeline():
p = Pipeline()
p.name = 'ML'
s1 = Stage()
s1.name = 'Generator-ML'
# the generator/ML Pipeline will consist of 1 Stage, 2 Tasks Task 1 :
# Generator; Task 2: ConvNet/Active Learning Model
# NOTE: Generator and ML/AL are alive across the whole workflow execution.
# For local testing, sleep time is longer than the total execution time of
# the MD pipelines.
t1 = Task()
t1.name = "generator"
t1.pre_exec = [
# 'module load python/2.7.15-anaconda2-5.3.0',
# 'module load cuda/9.1.85',
# 'module load gcc/6.4.0',
# 'source activate snakes'
]
# t1.executable = ['python']
# t1.arguments = ['/ccs/home/jdakka/tf.py']
t1.executable = ['sleep']
t1.arguments = ['5']
s1.add_tasks(t1)
t2 = Task()
t2.name = "ml-al"
t2.pre_exec = [
# 'module load python/2.7.15-anaconda2-5.3.0',
# 'module load cuda/9.1.85',
# 'module load gcc/6.4.0',
# 'source activate snakes'
]
# t2.executable = ['python']
# t2.arguments = ['/ccs/home/jdakka/tf.py']
t2.executable = ['sleep']
t2.arguments = ['10']
s1.add_tasks(t2)
# Add Stage to the Pipeline
p.add_stages(s1)
return p
def GenerateStage(scfg, ecfg, pipe_name, stage_name):
# Initialize a stage object
s = Stage()
# Provide a name for this stage
s.name = stage_name
# Loop through the tasks for this stage
for this_task in scfg.keys():
# Populate the stage object with the tasks
s.add_tasks(
GenerateTask(scfg[this_task], ecfg, pipe_name, stage_name,
this_task))
# Return the stage object
return (s)
def generate_MD_tasks(self):
"""
Function to generate MD tasks.
"""
p = Pipeline()
p.name = "MD"
s1 = Stage()
s1.name = 'MD'
# MD tasks
for i in range(self.num_MD):
t1 = Task()
# https://github.com/radical-collaboration/hyperspace/blob/MD/microscope/experiments/MD_exps/fs-pep/run_openmm.py
t1.pre_exec = ['. /sw/summit/python/2.7/anaconda2/5.3.0/etc/profile.d/conda.sh']
t1.pre_exec += ['module load cuda/10.1.168']
t1.pre_exec += ['conda activate %s' % conda_path]
t1.pre_exec += ['export PYTHONPATH=%s/MD_exps:$PYTHONPATH' % base_path]
t1.pre_exec += ['cd %s' % md_path]
# t1.pre_exec += [f"sleep {i}"]
t1.executable = ['%s/bin/python' % conda_path] # run_openmm.py
t1.arguments = ['%s/run_openmm.py' % md_path]
t1.arguments += ['--pdb_file', pdb_file]
if top_file:
t1.arguments += ['--topol', top_file]
t1.arguments += ['--length', 1000]
# assign hardware the task
t1.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 4,
'thread_type': 'OpenMP'
}
t1.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': 'CUDA'
}
# Add the MD task to the simulating stage
s1.add_tasks(t1)
p.add_stages(s1)
return p
def generate_pipeline(name, stages): #generate the pipeline of prediction and blob detection
# Create a Pipeline object
p = Pipeline()
p.name = name
for s_cnt in range(stages):
# Create a Stage object
s = Stage()
s.name = 'Stage %s'%s_cnt
if(stage==1)
# Create Task 1, training
t = Task()
t.name = 'my-task1'
t.executable = ['sbatch'] # Assign executable to the task
# Assign arguments for the task executable
t.arguments = ['/Code/trainbatch.bat']
def generate_pipline(stages, tasks_per_stage=1):
p = Pipeline()
##Create 8 stages each with one task
for s_cnt in range(stages):
s = Stage()
s.name = 'stage %s' % (s_cnt + 1)
for t_cnt in range(tasks_per_stage):
t = Task()
t.name = 'task %s' % (t_cnt + 1)
t.executable = '/bin/sleep'
t.arguments = ['100']
# Add the Task to the Stage
s.add_tasks(t)
# Add Stage to the Pipeline
p.add_stages(s)
return p
def on_true():
global NUM_TASKS, CUR_STAGE
NUM_TASKS *= 2
s = Stage()
s.name = 's%s' % CUR_STAGE
for t in range(NUM_TASKS):
s.add_tasks(create_single_task())
s.post_exec = {
'condition': condition,
'on_true': on_true,
'on_false': on_false
}
p1.add_stages(s)
def describe_ML_pipline():
p = Pipeline()
p.name = 'ML'
# Learning stage
s1 = Stage()
s1.name = 'learning'
# Docking rescroring task
t1 = Task()
t1.executable = ['/gpfs/alpine/scratch/mturilli1/bip179/bin/run_learner_wrapper.sh']
# Add the docking rescroring task to the docking rescroring stage
s1.add_tasks(t1)
# Add the docking rescroring stage to the pipeline
p.add_stages(s1)
return p
def test_integration_local():
"""
**Purpose**: Run an EnTK application on localhost
"""
def create_single_task():
t1 = Task()
t1.name = 'simulation'
t1.executable = '/bin/echo'
t1.arguments = ['hello']
t1.copy_input_data = []
t1.copy_output_data = []
return t1
p1 = Pipeline()
p1.name = 'p1'
s = Stage()
s.name = 's1'
s.tasks = create_single_task()
s.add_tasks(create_single_task())
p1.add_stages(s)
res_dict = {
'resource': 'local.localhost',
'walltime': 5,
'cpus': 1,
'project': ''
}
appman = AppManager(hostname=hostname, port=port)
appman.resource_desc = res_dict
appman.workflow = [p1]
appman.run()
def test_integration_local():
"""
**Purpose**: Run an EnTK application on localhost
"""
def create_single_task():
t1 = Task()
t1.name = 'simulation'
t1.executable = ['/bin/echo']
t1.arguments = ['hello']
t1.copy_input_data = []
t1.copy_output_data = []
return t1
p1 = Pipeline()
p1.name = 'p1'
s = Stage()
s.name = 's1'
s.tasks = create_single_task()
s.add_tasks(create_single_task())
p1.add_stages(s)
res_dict = {
'resource': 'local.localhost',
'walltime': 5,
'cpus': 1,
'project': ''
}
os.environ['RADICAL_PILOT_DBURL'] = MLAB
appman = AppManager(hostname=hostname, port=port)
appman.resource_desc = res_dict
appman.workflow = [p1]
appman.run()
def constructTask(url):
response = requests.get(url)
response = response.json()
sourceParallelism = response['sourceParallelism']
itr = response['itr']
# Create a Stage object
s1 = Stage()
s1.name = 'Stage 1'
for i in range sourceParallelism:
t = Task()
t.name = 'Generator ' + str(i)
t.executable = ['python3']
t.arguments = ['/home/divyaprakash/EnTK/share/radical.entk/user_guide/scripts/generator'+i+'.py', sourceParallelism]
s1.add_task(t)
return stage
def generate_interfacing_task(self):
p = Pipeline()
p.name = 'interfacing'
s4 = Stage()
s4.name = 'scanning'
# Scaning for outliers and prepare the next stage of MDs
t4 = Task()
t4.pre_exec = []
t4.pre_exec += ['. /sw/summit/python/2.7/anaconda2/5.3.0/etc/profile.d/conda.sh']
t4.pre_exec += ['module load cuda/10.1.168']
t4.pre_exec += ['conda activate %s' % conda_path]
t4.pre_exec += ['export PYTHONPATH=%s/CVAE_exps:$PYTHONPATH' % base_path]
t4.pre_exec += ['cd %s/Outlier_search' % base_path]
t4.executable = ['%s/bin/python' % conda_path]
t4.arguments = [
'outlier_locator.py',
'--md', md_path,
'--cvae', cvae_path,
'--pdb', pdb_file,
'--ref', ref_pdb_file,
'--n_out', self.num_outliers,
'--timeout', self.t_timeout]
t4.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 12,
'thread_type': 'OpenMP'
}
t4.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': 'CUDA'
}
s4.add_tasks(t4)
p.add_stages(s4)
return p
def setup_replicas(replicas, min_temp, max_temp, timesteps, basename):
writeInputs.writeInputs(max_temp=max_temp, min_temp=min_temp, replicas=replicas, timesteps=timesteps, basename=basename)
tar = tarfile.open("input_files.tar", "w")
for name in [basename + ".prmtop", basename + ".inpcrd", basename + ".mdin"]:
tar.add(name)
for r in range(replicas):
tar.add('mdin-{replica}-{cycle}'.format(replica=r, cycle=0))
tar.close()
for r in range(replicas):
os.remove('mdin-{replica}-{cycle}'.format(replica=r, cycle=0))
setup_p = Pipeline()
setup_p.name = 'untarPipe'
repo = git.Repo('.', search_parent_directories=True)
aux_function_path = repo.working_tree_dir
untar_stg = Stage()
untar_stg.name = 'untarStg'
#Untar Task
untar_tsk = Task()
untar_tsk.name = 'untarTsk'
untar_tsk.executable = ['python']
untar_tsk.upload_input_data = ['untar_input_files.py', 'input_files.tar']
untar_tsk.arguments = ['untar_input_files.py', 'input_files.tar']
untar_tsk.cpu_reqs = 1
untar_tsk.post_exec = []
untar_stg.add_tasks(untar_tsk)
setup_p.add_stages(untar_stg)
global replica_sandbox
replica_sandbox='$Pipeline_%s_Stage_%s_Task_%s'%(setup_p.name, untar_stg.name, untar_tsk.name)
print replica_sandbox
return setup_p
def describe_MD_pipline(t2_senv):
p = Pipeline()
p.name = 'MD'
# Ligand parameterization stage
# s1 = Stage()
# s1.name = 'parameterization'
# ligand parameterization task
# t1 = Task()
# t1.executable = ['sleep']
# t1.arguments = ['30']
# Add the parameterization task to the parameterization stage
# s1.add_tasks(t1)
# Add parameterization stage to the pipeline
# p.add_stages(s1)
# Docking rescroring stage
s2 = Stage()
s2.name = 'rescoring'
# Docking rescroring task
t2 = Task()
# t2.pre_exec = t2_senv
# t2.executable = ['python']
# t2.arguments = ['1_mmgbsa.py', '-p', '"test"', '-n', '0']
t2.executable = [
'/gpfs/alpine/scratch/mturilli1/bip179/bin/mmgbsa_wrapper.sh'
]
# Add the docking rescroring task to the docking rescroring stage
s2.add_tasks(t2)
# Add the docking rescroring stage to the pipeline
p.add_stages(s2)
return p
def generate_molecular_dynamics_stage(self) -> Stage:
stage = Stage()
stage.name = self.MOLECULAR_DYNAMICS_STAGE_NAME
cfg = self.cfg.molecular_dynamics_stage
stage_api = self.api.molecular_dynamics_stage
if self.stage_idx == 0:
filenames = self.api.get_initial_pdbs(
cfg.task_config.initial_pdb_dir)
filenames = itertools.cycle(filenames)
else:
filenames = None
for task_idx in range(cfg.num_tasks):
output_path = stage_api.task_dir(self.stage_idx,
task_idx,
mkdir=True)
assert output_path is not None
# Update base parameters
cfg.task_config.experiment_directory = self.cfg.experiment_directory
cfg.task_config.stage_idx = self.stage_idx
cfg.task_config.task_idx = task_idx
cfg.task_config.node_local_path = self.cfg.node_local_path
cfg.task_config.output_path = output_path
if self.stage_idx == 0:
assert filenames is not None
cfg.task_config.pdb_file = next(filenames)
else:
cfg.task_config.pdb_file = None
cfg_path = stage_api.config_path(self.stage_idx, task_idx)
cfg.task_config.dump_yaml(cfg_path)
task = generate_task(cfg)
task.arguments += ["-c", cfg_path.as_posix()]
stage.add_tasks(task)
return stage
def test_stage_exceptions(t, l, i, b, se):
"""
***Purpose***: Test if correct exceptions are raised when attributes are assigned unacceptable values.
"""
s = Stage()
data_type = [t, l, i, b, se]
for data in data_type:
print 'Using: %s, %s' % (data, type(data))
if not isinstance(data, str):
with pytest.raises(TypeError):
s.name = data
with pytest.raises(TypeError):
s.tasks = data
with pytest.raises(TypeError):
s.add_tasks(data)
def generate_aggregating_stage():
"""
Function to concatenate the MD trajectory (h5 contact map)
"""
s2 = Stage()
s2.name = 'aggregating'
# Aggregation task
t2 = Task()
# https://github.com/radical-collaboration/hyperspace/blob/MD/microscope/experiments/MD_to_CVAE/MD_to_CVAE.py
t2.pre_exec = []
t2.pre_exec += [
'. /sw/summit/python/2.7/anaconda2/5.3.0/etc/profile.d/conda.sh'
]
t2.pre_exec += ['conda activate %s' % conda_path]
t2.pre_exec += ['cd %s' % agg_path]
t2.executable = ['%s/bin/python' % conda_path] # MD_to_CVAE.py
t2.arguments = ['%s/MD_to_CVAE.py' % agg_path, '--sim_path', md_path]
# Add the aggregation task to the aggreagating stage
s2.add_tasks(t2)
return s2
def generate_pipeline():
# Create a Pipeline object
p = Pipeline()
p.name = 'p1'
# Create a Stage object
s1 = Stage()
s1.name = 's1'
# Create 4K tasks to ensure we don't hit any RMQ connection drops
for _ in range(4096):
t1 = Task()
t1.executable = ['/bin/echo']
t1.arguments = ['"Hello World"']
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
return p
def generate_pipeline():
# Create a Pipeline object
p = Pipeline()
p.name = 'p1'
# Create a Stage object
s1 = Stage()
s1.name = 's1'
# Create a Task object which creates a file named 'output.txt' of size 1 MB
t1 = Task()
t1.name = 't1'
t1.executable = ['/bin/false']
# t1.arguments = ['"Hello World"','>>','temp.txt']
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
return p
def test_stage_exceptions(t, l, i, b, se):
"""
***Purpose***: Test if correct exceptions are raised when attributes are
assigned unacceptable values.
"""
s = Stage()
data_type = [t, l, i, b, se]
for data in data_type:
print 'Using: %s, %s' % (data, type(data))
if not isinstance(data, str):
with pytest.raises(TypeError):
s.name = data
with pytest.raises(TypeError):
s.tasks = data
with pytest.raises(TypeError):
s.add_tasks(data)
def test_stage_pass_uid():
s = Stage()
s._uid = 's'
s.name = 's1'
s.parent_pipeline['uid'] = 'p'
s.parent_pipeline['name'] = 'p1'
t1 = Task()
t2 = Task()
s.add_tasks([t1,t2])
s._pass_uid()
assert t1.parent_stage['uid'] == s.uid
assert t1.parent_stage['name'] == s.name
assert t1.parent_pipeline['uid'] == s.parent_pipeline['uid']
assert t1.parent_pipeline['name'] == s.parent_pipeline['name']
assert t2.parent_stage['uid'] == s.uid
assert t2.parent_stage['name'] == s.name
assert t2.parent_pipeline['uid'] == s.parent_pipeline['uid']
assert t2.parent_pipeline['name'] == s.parent_pipeline['name']
def init_cycle(self, replicas, replica_cores, python_path, md_executable, exchange_method, min_temp, max_temp, timesteps, basename, pre_exec): # "cycle" = 1 MD stage plus the subsequent exchange computation
"""
Initial cycle consists of:
1) Create tarball of MD input data
2) Transfer the tarball to pilot sandbox
3) Untar the tarball
4) Run first cycle
"""
#Initialize Pipeline
self._prof.prof('InitTar', uid=self._uid)
p = Pipeline()
p.name = 'initpipeline'
md_dict = dict() #bookkeeping
tar_dict = dict() #bookkeeping
#Write the input files
self._prof.prof('InitWriteInputs', uid=self._uid)
writeInputs.writeInputs(
max_temp=max_temp,
min_temp=min_temp,
replicas=replicas,
timesteps=timesteps,
basename=basename)
self._prof.prof('EndWriteInputs', uid=self._uid)
self._prof.prof('InitTar', uid=self._uid)
#Create Tarball of input data
tar = tarfile.open("input_files.tar", "w")
for name in [
basename + ".prmtop", basename + ".inpcrd", basename + ".mdin"
]:
tar.add(name)
for r in range(replicas):
tar.add('mdin_{0}'.format(r))
tar.close()
#delete all input files outside the tarball
for r in range(replicas):
os.remove('mdin_{0}'.format(r))
self._prof.prof('EndTar', uid=self._uid)
#Create Untar Stage
repo = git.Repo('.', search_parent_directories=True)
aux_function_path = repo.working_tree_dir
untar_stg = Stage()
untar_stg.name = 'untarStg'
#Untar Task
untar_tsk = Task()
untar_tsk.name = 'untartsk'
untar_tsk.executable = ['python']
untar_tsk.upload_input_data = [
str(aux_function_path)+'/repex/untar_input_files.py', 'input_files.tar'
]
untar_tsk.arguments = ['untar_input_files.py', 'input_files.tar']
untar_tsk.cpu_reqs = 1
#untar_tsk.post_exec = ['']
untar_stg.add_tasks(untar_tsk)
p.add_stages(untar_stg)
tar_dict[0] = '$Pipeline_%s_Stage_%s_Task_%s' % (
p.name, untar_stg.name, untar_tsk.name)
# First MD stage: needs to be defined separately since workflow is not built from a predetermined order, also equilibration needs to happen first.
md_stg = Stage()
md_stg.name = 'mdstg0'
self._prof.prof('InitMD_0', uid=self._uid)
# MD tasks
for r in range(replicas):
md_tsk = AMBERTask(cores=replica_cores, md_executable=md_executable, pre_exec=pre_exec)
md_tsk.name = 'mdtsk-{replica}-{cycle}'.format(replica=r, cycle=0)
md_tsk.link_input_data += [
'%s/inpcrd' % tar_dict[0],
'%s/prmtop' % tar_dict[0],
'%s/mdin_{0}'.format(r) %
tar_dict[0] #Use for full temperature exchange
]
md_tsk.arguments = [
'-O',
'-p',
'prmtop',
'-i',
'mdin_{0}'.format(r),
'-c',
'inpcrd',
'-o',
'out-{replica}-{cycle}'.format(replica=r, cycle=0),
'-r',
'restrt'.format(replica=r, cycle=0),
#'-r', 'rstrt-{replica}-{cycle}'.format(replica=r,cycle=0),
'-x',
'mdcrd-{replica}-{cycle}'.format(replica=r, cycle=0),
#'-o', '$NODE_LFS_PATH/out-{replica}-{cycle}'.format(replica=r,cycle=0),
#'-r', '$NODE_LFS_PATH/rstrt-{replica}-{cycle}'.format(replica=r,cycle=0),
#'-x', '$NODE_LFS_PATH/mdcrd-{replica}-{cycle}'.format(replica=r,cycle=0),
'-inf',
'mdinfo_{0}'.format(r)
]
md_dict[r] = '$Pipeline_%s_Stage_%s_Task_%s' % (
p.name, md_stg.name, md_tsk.name)
md_stg.add_tasks(md_tsk)
self.md_task_list.append(md_tsk)
#print md_tsk.uid
p.add_stages(md_stg)
#stage_uids.append(md_stg.uid)
# First Exchange Stage
ex_stg = Stage()
ex_stg.name = 'exstg0'
self._prof.prof('InitEx_0', uid=self._uid)
# Create Exchange Task
ex_tsk = Task()
ex_tsk.name = 'extsk0'
#ex_tsk.pre_exec = ['module load python/2.7.10']
ex_tsk.executable = [python_path]
ex_tsk.upload_input_data = [exchange_method]
for r in range(replicas):
ex_tsk.link_input_data += ['%s/mdinfo_%s' % (md_dict[r], r)]
ex_tsk.pre_exec = ['mv *.py exchange_method.py']
ex_tsk.arguments = ['exchange_method.py', '{0}'.format(replicas), '0']
ex_tsk.cores = 1
ex_tsk.mpi = False
ex_tsk.download_output_data = ['exchangePairs_0.dat']
ex_stg.add_tasks(ex_tsk)
#task_uids.append(ex_tsk.uid)
p.add_stages(ex_stg)
self.ex_task_list.append(ex_tsk)
#self.ex_task_uids.append(ex_tsk.uid)
self.book.append(md_dict)
return p
def test_rp_da_scheduler_bw():
"""
**Purpose**: Run an EnTK application on localhost
"""
p1 = Pipeline()
p1.name = 'p1'
n = 10
s1 = Stage()
s1.name = 's1'
for x in range(n):
t = Task()
t.name = 't%s'%x
t.executable = ['/bin/hostname']
t.arguments = ['>','hostname.txt']
t.cpu_reqs['processes'] = 1
t.cpu_reqs['threads_per_process'] = 16
t.cpu_reqs['thread_type'] = ''
t.cpu_reqs['process_type'] = ''
t.lfs_per_process = 10
t.download_output_data = ['hostname.txt > s1_t%s_hostname.txt'%(x)]
s1.add_tasks(t)
p1.add_stages(s1)
s2 = Stage()
s2.name = 's2'
for x in range(n):
t = Task()
t.executable = ['/bin/hostname']
t.arguments = ['>','hostname.txt']
t.cpu_reqs['processes'] = 1
t.cpu_reqs['threads_per_process'] = 16
t.cpu_reqs['thread_type'] = ''
t.cpu_reqs['process_type'] = ''
t.download_output_data = ['hostname.txt > s2_t%s_hostname.txt'%(x)]
t.tag = 't%s'%x
s2.add_tasks(t)
p1.add_stages(s2)
res_dict = {
'resource' : 'ncsa.bw_aprun',
'walltime' : 10,
'cpus' : 128,
'project' : 'gk4',
'queue' : 'high'
}
os.environ['RADICAL_PILOT_DBURL'] = MLAB
appman = AppManager(hostname=hostname, port=port)
appman.resource_desc = res_dict
appman.workflow = [p1]
appman.run()
for i in range(n):
assert open('s1_t%s_hostname.txt'%i,'r').readline().strip() == open('s2_t%s_hostname.txt'%i,'r').readline().strip()
txts = glob('%s/*.txt' % os.getcwd())
for f in txts:
os.remove(f)
def generate_pipeline():
# Create a Pipeline object
p = Pipeline()
p.name = 'p1'
# Create a Stage object
s1 = Stage()
s1.name = 's1'
# Create a Task object which creates a file named 'output.txt' of size 1 MB
t1 = Task()
t1.name = 't1'
t1.executable = '/bin/bash'
t1.arguments = ['-l', '-c', 'base64 /dev/urandom | head -c 1000000 > output.txt']
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
# Create another Stage object to hold character count tasks
s2 = Stage()
s2.name = 's2'
s2_task_uids = []
for cnt in range(30):
# Create a Task object
t2 = Task()
t2.name = 't%s' % (cnt + 1)
t2.executable = '/bin/bash'
t2.arguments = ['-l', '-c', 'grep -o . output.txt | sort | uniq -c > ccount.txt']
# Copy data from the task in the first stage to the current task's location
t2.copy_input_data = ['$Pipeline_%s_Stage_%s_Task_%s/output.txt' % (p.name, s1.name, t1.name)]
# Add the Task to the Stage
s2.add_tasks(t2)
s2_task_uids.append(t2.name)
# Add Stage to the Pipeline
p.add_stages(s2)
# Create another Stage object to hold checksum tasks
s3 = Stage()
s3.name = 's3'
for cnt in range(30):
# Create a Task object
t3 = Task()
t3.name = 't%s' % (cnt + 1)
t3.executable = '/bin/bash'
t3.arguments = ['-l', '-c', 'sha1sum ccount.txt > chksum.txt']
# Copy data from the task in the first stage to the current task's location
t3.copy_input_data = ['$Pipeline_%s_Stage_%s_Task_%s/ccount.txt' % (p.name, s2.name, s2_task_uids[cnt])]
# Download the output of the current task to the current location
t3.download_output_data = ['chksum.txt > chksum_%s.txt' % cnt]
# Add the Task to the Stage
s3.add_tasks(t3)
# Add Stage to the Pipeline
p.add_stages(s3)
return p
# Description of how the RabbitMQ process is accessible
# No need to change/set any variables if you installed RabbitMQ has a system
# process. If you are running RabbitMQ under a docker container or another
# VM, set "RMQ_HOSTNAME" and "RMQ_PORT" in the session where you are running
# this script.
hostname = os.environ.get('RMQ_HOSTNAME', 'localhost')
port = os.environ.get('RMQ_PORT', 5672)
if __name__ == '__main__':
# Create a Pipeline object
p = Pipeline()
# Create a Stage object
s1 = Stage()
s1.name = 'Stage 1'
for cnt in range(10):
# Create a Task object
t = Task()
t.name = 'my-task' # Assign a name to the task (optional)
t.executable = '/bin/echo' # Assign executable to the task
t.arguments = ['I am task %s in %s'%(cnt, s1.name)] # Assign arguments for the task executable
# Add the Task to the Stage
s1.add_tasks(t)
# Add Stage to the Pipeline
p.add_stages(s1)
def GeneralCycle(self, Replicas, Replica_Cores, Cycle, MD_Executable, ExchangeMethod):
"""
All cycles after the initial cycle
Pulls up exchange pairs file and generates the new workflow
"""
self._prof.prof('InitcreateMDwokflow_{0}'.format(Cycle), uid=self._uid)
with open('exchangePairs_{0}.dat'.format(Cycle),'r') as f: # Read exchangePairs.dat
ExchangeArray = []
for line in f:
ExchangeArray.append(int(line.split()[1]))
#ExchangeArray.append(line)
#print ExchangeArray
q = Pipeline()
q.name = 'genpipeline{0}'.format(Cycle)
#Bookkeeping
stage_uids = list()
task_uids = list() ## = dict()
md_dict = dict()
#Create initial MD stage
md_stg = Stage()
md_stg.name = 'mdstage{0}'.format(Cycle)
self._prof.prof('InitMD_{0}'.format(Cycle), uid=self._uid)
for r in range (Replicas):
md_tsk = AMBERTask(cores=Replica_Cores, MD_Executable=MD_Executable)
md_tsk.name = 'mdtsk-{replica}-{cycle}'.format(replica=r,cycle=Cycle)
md_tsk.link_input_data = ['%s/restrt > inpcrd'%(self.Book[Cycle-1][ExchangeArray[r]]),
'%s/prmtop'%(self.Book[0][r]),
#'%s/prmtop'%(self.Tarball_path[0]),
'%s/mdin_{0}'.format(r)%(self.Book[0][r])]
#'%s/mdin'%(self.Book[0][r])]
#'%s/mdin'%(self.Tarball_path[0])]
md_tsk.arguments = ['-O', '-i', 'mdin_{0}'.format(r), '-p', 'prmtop', '-c', 'inpcrd', '-o', 'out_{0}'.format(r),'-inf', 'mdinfo_{0}'.format(r)]
#md_tsk.arguments = ['-O', '-i', 'mdin', '-p', 'prmtop', '-c', 'inpcrd', '-o', 'out_{0}'.format(r),'-inf', 'mdinfo_{0}'.format(r)]
md_dict[r] = '$Pipeline_%s_Stage_%s_Task_%s'%(q.name, md_stg.name, md_tsk.name)
self.md_task_list.append(md_tsk)
md_stg.add_tasks(md_tsk)
q.add_stages(md_stg)
ex_stg = Stage()
ex_stg.name = 'exstg{0}'.format(Cycle+1)
#Create Exchange Task
ex_tsk = Task()
ex_tsk.name = 'extsk{0}'.format(Cycle+1)
ex_tsk.executable = ['python']
ex_tsk.upload_input_data = [ExchangeMethod]
for r in range (Replicas):
ex_tsk.link_input_data += ['%s/mdinfo_%s'%(md_dict[r],r)]
ex_tsk.arguments = ['TempEx.py','{0}'.format(Replicas), '{0}'.format(Cycle+1)]
ex_tsk.cores = 1
ex_tsk.mpi = False
ex_tsk.download_output_data = ['exchangePairs_{0}.dat'.format(Cycle+1)] # Finds exchange partners, also Generates exchange history trace
ex_stg.add_tasks(ex_tsk)
#task_uids.append(ex_tsk.uid)
self.ex_task_list.append(ex_tsk)
q.add_stages(ex_stg)
#stage_uids.append(ex_stg.uid)
self.Book.append(md_dict)
#self._prof.prof('EndEx_{0}'.format(Cycle), uid=self._uid)
#print d
#print self.Book
return q
def test_create_cud_from_task():
"""
**Purpose**: Test if the 'create_cud_from_task' function generates a RP ComputeUnitDescription with the complete
Task description
"""
pipeline = 'p1'
stage = 's1'
task = 't1'
placeholder_dict = {
pipeline: {
stage: {
task: '/home/vivek/some_file.txt'
}
}
}
t1 = Task()
t1.name = 't1'
t1.pre_exec = ['module load gromacs']
t1.executable = ['grompp']
t1.arguments = ['hello']
t1.cpu_reqs = {'processes': 4,
'process_type': 'MPI',
'threads_per_process': 1,
'thread_type': 'OpenMP'
}
t1.gpu_reqs = {'processes': 4,
'process_type': 'MPI',
'threads_per_process': 2,
'thread_type': 'OpenMP'
}
t1.post_exec = ['echo test']
t1.upload_input_data = ['upload_input.dat']
t1.copy_input_data = ['copy_input.dat']
t1.link_input_data = ['link_input.dat']
t1.copy_output_data = ['copy_output.dat']
t1.download_output_data = ['download_output.dat']
p = Pipeline()
p.name = 'p1'
s = Stage()
s.name = 's1'
s.tasks = t1
p.stages = s
p._assign_uid('test')
cud = create_cud_from_task(t1, placeholder_dict)
assert cud.name == '%s,%s,%s,%s,%s,%s' % (t1.uid, t1.name,
t1.parent_stage['uid'], t1.parent_stage['name'],
t1.parent_pipeline['uid'], t1.parent_pipeline['name'])
assert cud.pre_exec == t1.pre_exec
# rp returns executable as a string regardless of whether assignment was using string or list
assert cud.executable == t1.executable
assert cud.arguments == t1.arguments
assert cud.cpu_processes == t1.cpu_reqs['processes']
assert cud.cpu_threads == t1.cpu_reqs['threads_per_process']
assert cud.cpu_process_type == t1.cpu_reqs['process_type']
assert cud.cpu_thread_type == t1.cpu_reqs['thread_type']
assert cud.gpu_processes == t1.gpu_reqs['processes']
assert cud.gpu_threads == t1.gpu_reqs['threads_per_process']
assert cud.gpu_process_type == t1.gpu_reqs['process_type']
assert cud.gpu_thread_type == t1.gpu_reqs['thread_type']
assert cud.post_exec == t1.post_exec
assert {'source': 'upload_input.dat', 'target': 'upload_input.dat'} in cud.input_staging
assert {'source': 'copy_input.dat', 'action': rp.COPY, 'target': 'copy_input.dat'} in cud.input_staging
assert {'source': 'link_input.dat', 'action': rp.LINK, 'target': 'link_input.dat'} in cud.input_staging
assert {'source': 'copy_output.dat', 'action': rp.COPY, 'target': 'copy_output.dat'} in cud.output_staging
assert {'source': 'download_output.dat', 'target': 'download_output.dat'} in cud.output_staging
def InitCycle(self, Replicas, Replica_Cores, md_executable, ExchangeMethod, timesteps): # "Cycle" = 1 MD stage plus the subsequent exchange computation
"""
Initial cycle consists of:
1) Create tarball of MD input data
2) Transfer the tarball to pilot sandbox
3) Untar the tarball
4) Run first Cycle
"""
#Initialize Pipeline
#self._prof.prof('InitTar', uid=self._uid)
p = Pipeline()
p.name = 'initpipeline'
md_dict = dict() #Bookkeeping
tar_dict = dict() #Bookkeeping
##Write the input files
self._prof.prof('InitWriteInputs', uid=self._uid)
writeInputs.writeInputs(max_temp=350,min_temp=250,replicas=Replicas,timesteps=timesteps)
self._prof.prof('EndWriteInputs', uid=self._uid)
self._prof.prof('InitTar', uid=self._uid)
#Create Tarball of input data
tar = tarfile.open("Input_Files.tar","w")
for name in ["prmtop", "inpcrd", "mdin"]:
tar.add(name)
for r in range (Replicas):
tar.add('mdin_{0}'.format(r))
tar.close()
#delete all input files outside the tarball
for r in range (Replicas):
os.remove('mdin_{0}'.format(r))
self._prof.prof('EndTar', uid=self._uid)
#Create Untar Stage
untar_stg = Stage()
untar_stg.name = 'untarStg'
#Untar Task
untar_tsk = Task()
untar_tsk.name = 'untartsk'
untar_tsk.executable = ['python']
untar_tsk.upload_input_data = ['untar_input_files.py','Input_Files.tar']
untar_tsk.arguments = ['untar_input_files.py','Input_Files.tar']
untar_tsk.cores = 1
untar_stg.add_tasks(untar_tsk)
p.add_stages(untar_stg)
tar_dict[0] = '$Pipeline_%s_Stage_%s_Task_%s'%(p.name,
untar_stg.name,
untar_tsk.name)
# First MD stage: needs to be defined separately since workflow is not built from a predetermined order
md_stg = Stage()
md_stg.name = 'mdstg0'
self._prof.prof('InitMD_0', uid=self._uid)
# MD tasks
for r in range (Replicas):
md_tsk = AMBERTask(cores=Replica_Cores, MD_Executable=md_executable)
md_tsk.name = 'mdtsk-{replica}-{cycle}'.format(replica=r,cycle=0)
md_tsk.link_input_data += [
'%s/inpcrd'%tar_dict[0],
'%s/prmtop'%tar_dict[0],
'%s/mdin_{0}'.format(r)%tar_dict[0] #Use for full temperature exchange
#'%s/mdin'%tar_dict[0] #Testing only
]
md_tsk.arguments = ['-O','-p','prmtop', '-i', 'mdin_{0}'.format(r), # Use this for full Temperature Exchange
'-c','inpcrd','-o','out_{0}'.format(r),
'-inf','mdinfo_{0}'.format(r)]
md_dict[r] = '$Pipeline_%s_Stage_%s_Task_%s'%(p.name, md_stg.name, md_tsk.name)
md_stg.add_tasks(md_tsk)
self.md_task_list.append(md_tsk)
#print md_tsk.uid
p.add_stages(md_stg)
#stage_uids.append(md_stg.uid)
# First Exchange Stage
ex_stg = Stage()
ex_stg.name = 'exstg0'
self._prof.prof('InitEx_0', uid=self._uid)
#with open('logfile.log', 'a') as logfile:
# logfile.write( '%.5f' %time.time() + ',' + 'InitEx0' + '\n')
# Create Exchange Task. Exchange task performs a Metropolis Hastings thermodynamic balance condition
# check and spits out the exchangePairs.dat file that contains a sorted list of ordered pairs.
# Said pairs then exchange configurations by linking output configuration files appropriately.
ex_tsk = Task()
ex_tsk.name = 'extsk0'
ex_tsk.executable = ['python']
ex_tsk.upload_input_data = [ExchangeMethod]
for r in range (Replicas):
ex_tsk.link_input_data += ['%s/mdinfo_%s'%(md_dict[r],r)]
ex_tsk.arguments = ['TempEx.py','{0}'.format(Replicas), '0']
ex_tsk.cores = 1
ex_tsk.mpi = False
ex_tsk.download_output_data = ['exchangePairs_0.dat']
ex_stg.add_tasks(ex_tsk)
#task_uids.append(ex_tsk.uid)
p.add_stages(ex_stg)
self.ex_task_list.append(ex_tsk)
#self.ex_task_uids.append(ex_tsk.uid)
self.Book.append(md_dict)
return p
def general_cycle(self, replicas, replica_cores, cycle, python_path, md_executable, exchange_method, pre_exec):
"""
All cycles after the initial cycle
Pulls up exchange pairs file and generates the new workflow
"""
self._prof.prof('InitcreateMDwokflow_{0}'.format(cycle), uid=self._uid)
with open('exchangePairs_{0}.dat'.format(cycle),
'r') as f: # Read exchangePairs.dat
exchange_array = []
for line in f:
exchange_array.append(int(line.split()[1]))
#exchange_array.append(line)
#print exchange_array
q = Pipeline()
q.name = 'genpipeline{0}'.format(cycle)
#bookkeeping
stage_uids = list()
task_uids = list() ## = dict()
md_dict = dict()
#Create MD stage
md_stg = Stage()
md_stg.name = 'mdstage{0}'.format(cycle)
self._prof.prof('InitMD_{0}'.format(cycle), uid=self._uid)
for r in range(replicas):
md_tsk = AMBERTask(cores=replica_cores, md_executable=md_executable, pre_exec=pre_exec)
md_tsk.name = 'mdtsk-{replica}-{cycle}'.format(
replica=r, cycle=cycle)
md_tsk.link_input_data = [
'%s/restrt > inpcrd' %
(self.book[cycle - 1][exchange_array[r]]),
'%s/prmtop' % (self.book[0][r]),
'%s/mdin_{0}'.format(r) % (self.book[0][r])
]
### The Following softlinking scheme is to be used ONLY if node local file system is to be used: not fully supported yet.
#md_tsk.link_input_data = ['$NODE_LFS_PATH/rstrt-{replica}-{cycle}'.format(replica=exchange_array[r],cycle=cycle-1) > '$NODE_LFS_PATH/inpcrd',
# #'%s/restrt > inpcrd'%(self.book[cycle-1][exchange_array[r]]),
# '%s/prmtop'%(self.book[0][r]),
# '%s/mdin_{0}'.format(r)%(self.Book[0][r])]
md_tsk.arguments = [
'-O',
'-i',
'mdin_{0}'.format(r),
'-p',
'prmtop',
'-c',
'inpcrd',
#'-c', 'rstrt-{replica}-{cycle}'.format(replica=r,cycle=cycle-1),
'-o',
'out-{replica}-{cycle}'.format(replica=r, cycle=cycle),
'-r',
'restrt',
#'-r', 'rstrt-{replica}-{cycle}'.format(replica=r,cycle=cycle),
'-x',
'mdcrd-{replica}-{cycle}'.format(replica=r, cycle=cycle),
'-inf',
'mdinfo_{0}'.format(r)
]
#md_tsk.tag = 'mdtsk-{replica}-{cycle}'.format(replica=r,cycle=0)
md_dict[r] = '$Pipeline_%s_Stage_%s_Task_%s' % (
q.name, md_stg.name, md_tsk.name)
self.md_task_list.append(md_tsk)
md_stg.add_tasks(md_tsk)
q.add_stages(md_stg)
ex_stg = Stage()
ex_stg.name = 'exstg{0}'.format(cycle + 1)
#Create Exchange Task
ex_tsk = Task()
ex_tsk.name = 'extsk{0}'.format(cycle + 1)
ex_tsk.executable = [python_path]#['/usr/bin/python'] #['/opt/python/bin/python']
ex_tsk.upload_input_data = [exchange_method]
for r in range(replicas):
ex_tsk.link_input_data += ['%s/mdinfo_%s' % (md_dict[r], r)]
ex_tsk.pre_exec = ['mv *.py exchange_method.py']
ex_tsk.arguments = [
'exchange_method.py', '{0}'.format(replicas), '{0}'.format(cycle + 1)
]
ex_tsk.cores = 1
ex_tsk.mpi = False
ex_tsk.download_output_data = [
'exchangePairs_{0}.dat'.format(cycle + 1)
] # Finds exchange partners, also Generates exchange history trace
ex_stg.add_tasks(ex_tsk)
#task_uids.append(ex_tsk.uid)
self.ex_task_list.append(ex_tsk)
q.add_stages(ex_stg)
#stage_uids.append(ex_stg.uid)
self.book.append(md_dict)
#self._prof.prof('EndEx_{0}'.format(cycle), uid=self._uid)
#print d
#print self.book
return q
s1 = Stage()
# Create a Task object which creates a file named 'output.txt' of size 1 MB
t1 = Task()
t1.executable = '/bin/bash'
t1.arguments = ['-l', '-c', 'base64 /dev/urandom | head -c 1000000 > output.txt']
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
# Create another Stage object
s2 = Stage()
s2.name = 'Stage 2'
# Create a Task object
t2 = Task()
t2.executable = ['/bin/bash']
t2.arguments = ['-l', '-c', 'grep -o . output.txt | sort | uniq -c > ccount.txt']
# Copy data from the task in the first stage to the current task's location
t2.copy_input_data = ['$Pipline_%s_Stage_%s_Task_%s/output.txt' % (p.uid, s1.uid, t1.uid)]
# Download the output of the current task to the current location
t2.download_output_data = ['ccount.txt']
# Add the Task to the Stage
s2.add_tasks(t2)
# Add Stage to the Pipeline
p.add_stages(s2)
