def esmacs(self, rct_stage, stage, outdir="equilibration", name=None):
for i in range(1, 13):
t = Task()
t.pre_exec = [
"export WDIR=\"{}/{}\"".format(self.run_dir, name),
". {}".format(self.conda_init),
"conda activate {}".format(self.esmacs_tenv),
"module load {}".format(self.esmacs_tmodules),
"mkdir -p $WDIR/replicas/rep{}/{}".format(i, outdir),
"cd $WDIR/replicas/rep{}/{}".format(i, outdir),
"rm -f {}.log {}.xml {}.dcd {}.chk".format(
stage, stage, stage, stage), "export OMP_NUM_THREADS=1"
]
# t.executable = '/ccs/home/litan/miniconda3/envs/wf3/bin/python3.7'
t.executable = 'python3'
t.arguments = ['$WDIR/{}.py'.format(stage)]
t.post_exec = []
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'
}
getattr(self, rct_stage).add_tasks(t)
print(getattr(self, rct_stage).to_dict())
def esmacs(cfg, names, stage, outdir):
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()
t.pre_exec = [
"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)]
t.post_exec = []
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 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 test_assignment_exceptions():
t = Task()
data_type = [1, 'a', True, list()]
for data in data_type:
if not isinstance(data, str):
with pytest.raises(TypeError):
t.name = data
if not isinstance(data, list):
with pytest.raises(TypeError):
t.pre_exec = data
with pytest.raises(TypeError):
t.executable = data
with pytest.raises(TypeError):
t.arguments = data
with pytest.raises(TypeError):
t.post_exec = data
with pytest.raises(TypeError):
t.upload_input_data = data
with pytest.raises(TypeError):
t.copy_input_data = data
with pytest.raises(TypeError):
t.link_input_data = data
with pytest.raises(TypeError):
t.copy_output_data = data
with pytest.raises(TypeError):
t.download_output_data = data
def test_task_exceptions(s, l, i, b):
"""
**Purpose**: Test if all attribute assignments raise exceptions for invalid values
"""
t = Task()
data_type = [s, l, i, b]
for data in data_type:
if not isinstance(data, str):
with pytest.raises(TypeError):
t.name = data
with pytest.raises(TypeError):
t.path = data
with pytest.raises(TypeError):
t.parent_stage = data
with pytest.raises(TypeError):
t.parent_pipeline = data
with pytest.raises(TypeError):
t.stdout = data
with pytest.raises(TypeError):
t.stderr = data
if not isinstance(data, list):
with pytest.raises(TypeError):
t.pre_exec = data
with pytest.raises(TypeError):
t.executable = data
with pytest.raises(TypeError):
t.arguments = data
with pytest.raises(TypeError):
t.post_exec = data
with pytest.raises(TypeError):
t.upload_input_data = data
with pytest.raises(TypeError):
t.copy_input_data = data
with pytest.raises(TypeError):
t.link_input_data = data
with pytest.raises(TypeError):
t.move_input_data = data
with pytest.raises(TypeError):
t.copy_output_data = data
with pytest.raises(TypeError):
t.download_output_data = data
with pytest.raises(TypeError):
t.move_output_data = data
if not isinstance(data, str) and not isinstance(data, unicode):
with pytest.raises(ValueError):
t.cpu_reqs = {
'processes': 1,
'process_type': data,
'threads_per_process': 1,
'thread_type': None
}
t.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': data
}
t.gpu_reqs = {
'processes': 1,
'process_type': data,
'threads_per_process': 1,
'thread_type': None
}
t.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': data
}
if not isinstance(data, int):
with pytest.raises(TypeError):
t.cpu_reqs = {
'processes': data,
'process_type': None,
'threads_per_process': 1,
'thread_type': None
}
t.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': data,
'thread_type': None
}
t.gpu_reqs = {
'processes': data,
'process_type': None,
'threads_per_process': 1,
'thread_type': None
}
t.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': data,
'thread_type': None
}
'module load intel-mpi/intel/2018.3',
# Untar the input data
'tar -zxf specfem_data.tar.gz',
]
t1.executable = ['./bin/xspecfem3D']
t1.cpu_reqs = {
'processes': 4,
'process_type': 'MPI',
'threads_per_process': 1,
'thread_type': 'OpenMP'
}
t1.copy_input_data = ['/projects/TROMP/entk/scratch/specfem_data.tar.gz']
t1.post_exec = [ # Tar output files
'tar -zcf specfem_final.tar.gz bin DATA DATABASES_MPI OUTPUT_FILES',
# Copy to scratch folder
'cp specfem_final.tar.gz /projects/TROMP/entk/scratch/',
]
t1.download_output_data = ['STDOUT', 'STDERR', 'specfem_final.tar.gz']
specfem_stage.add_tasks(t1)
p.add_stages(specfem_stage)
res_dict = {
'resource': 'princeton.tiger_cpu',
'project': 'geo',
'queue': 'cpu',
'schema': 'local',
'walltime': 15,
'cpus': 4,
'threads_per_process': 0,
'thread_type': 'OpenMP'
}
t.gpu_reqs = {
'processes': 384,
'process_type': 'MPI',
'threads_per_process': 1,
'thread_type': 'OpenMP'
}
t.copy_input_data = [
'/lustre/atlas/scratch/vivekb/bip149/ssflow-N-seq-events/specfem_data_event_%s.tar'
% event,
'/lustre/atlas/scratch/vivekb/bip149/ssflow-N-seq-events/specfem_validator.py'
]
t.post_exec = [
'python specfem_validator.py OUTPUT_FILES/output_solver.txt'
]
specfem_stage.add_tasks(t2)
p.add_stages(specfem_stage)
res_dict = {
'resource': 'ornl.titan_aprun',
'walltime': 8 * num_events,
'cpus': 385,
'gpus': 385,
'project': 'BIP149',
'schema': 'local'
}
if num_events <= 16:
# Fits in debug queue
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'
placeholders = {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
cud = create_cud_from_task(t1, placeholders)
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.post_exec == t1.post_exec
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 {
'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
int(initial_config['test.ID.start']), '--test-ID-end',
int(initial_config['test.ID.end']), '--train-ID-start',
int(initial_config['train.ID.start']), '--train-ID-end',
int(initial_config['train.ID.end']), '--rolling',
int(initial_config['rolling']), '--members-size',
int(initial_config['members.size'])
])
t1.copy_input_data = [
'/work/vivek91/Temperature_NAM/Forecasts_NAM_C.nc',
'/work/vivek91/Temperature_NAM/Analysis_NAM_R.nc'
]
#t1.copy_output_data = ['{0} > /home/vivek91/{1}-{0}'.format(os.path.basename(initial_config['output.AnEn']), ind)]
t1.post_exec = ['rm *NAM*.nc']
if ind == 1:
stations_subset = initial_config['stations.ID'][ind *
10:(ind + 1) * 10]
#print t1.arguments
# Add this task to our stage
s1.add_tasks(t1)
# Add the stage to our pipeline
p.add_stages(s1)
# --------------------------------------------------------------------------
# Create a dictionary to describe our resource request
def test_task_exceptions(s,l,i,b):
"""
**Purpose**: Test if all attribute assignments raise exceptions for invalid values
"""
t = Task()
data_type = [s,l,i,b]
for data in data_type:
if not isinstance(data,str):
with pytest.raises(TypeError):
t.name = data
with pytest.raises(TypeError):
t.path = data
with pytest.raises(TypeError):
t.parent_stage = data
with pytest.raises(TypeError):
t.parent_pipeline = data
with pytest.raises(TypeError):
t.stdout = data
with pytest.raises(TypeError):
t.stderr = data
if not isinstance(data,list):
with pytest.raises(TypeError):
t.pre_exec = data
with pytest.raises(TypeError):
t.arguments = data
with pytest.raises(TypeError):
t.post_exec = data
with pytest.raises(TypeError):
t.upload_input_data = data
with pytest.raises(TypeError):
t.copy_input_data = data
with pytest.raises(TypeError):
t.link_input_data = data
with pytest.raises(TypeError):
t.move_input_data = data
with pytest.raises(TypeError):
t.copy_output_data = data
with pytest.raises(TypeError):
t.download_output_data = data
with pytest.raises(TypeError):
t.move_output_data = data
if not isinstance(data, str) and not isinstance(data, list):
with pytest.raises(TypeError):
t.executable = data
if not isinstance(data, str) and not isinstance(data, unicode):
with pytest.raises(ValueError):
t.cpu_reqs = {
'processes': 1,
'process_type': data,
'threads_per_process': 1,
'thread_type': None
}
t.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': data
}
t.gpu_reqs = {
'processes': 1,
'process_type': data,
'threads_per_process': 1,
'thread_type': None
}
t.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': data
}
if not isinstance(data, int):
with pytest.raises(TypeError):
t.cpu_reqs = {
'processes': data,
'process_type': None,
'threads_per_process': 1,
'thread_type': None
}
t.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': data,
'thread_type': None
}
t.gpu_reqs = {
'processes': data,
'process_type': None,
'threads_per_process': 1,
'thread_type': None
}
t.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': data,
'thread_type': None
}
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
