def test_crosssubtract_datamodel(self):
self.actualSetUp(zerow=True)
future_vis = arlexecute.scatter(self.vis_list[0])
future_skymodel_list = arlexecute.scatter(self.skymodel_list)
skymodel_vislist = predict_skymodel_list_arlexecute_workflow(
future_vis, future_skymodel_list, context='2d', docal=True)
skymodel_vislist = arlexecute.compute(skymodel_vislist, sync=True)
vobs = sum_predict_results(skymodel_vislist)
future_vobs = arlexecute.scatter(vobs)
skymodel_vislist = crosssubtract_datamodels_skymodel_list_arlexecute_workflow(
future_vobs, skymodel_vislist)
skymodel_vislist = arlexecute.compute(skymodel_vislist, sync=True)
result_skymodel = [
SkyModel(components=None, image=self.skymodel_list[-1].image)
for v in skymodel_vislist
]
self.vis_list = arlexecute.scatter(self.vis_list)
result_skymodel = invert_skymodel_list_arlexecute_workflow(
skymodel_vislist, result_skymodel, context='2d', docal=True)
results = arlexecute.compute(result_skymodel, sync=True)
assert numpy.max(numpy.abs(results[0][0].data)) > 0.0
assert numpy.max(numpy.abs(results[0][1])) > 0.0
if self.plot:
import matplotlib.pyplot as plt
from wrappers.arlexecute.image.operations import show_image
show_image(results[0][0],
title='Dirty image after cross-subtraction',
vmax=0.1,
vmin=-0.01)
plt.show()
def test_predict(self):
self.actualSetUp(zerow=True)
self.skymodel_list = [
arlexecute.execute(create_low_test_skymodel_from_gleam)(
npixel=self.npixel,
cellsize=self.cellsize,
frequency=[self.frequency[f]],
phasecentre=self.phasecentre,
polarisation_frame=PolarisationFrame("stokesI"),
flux_limit=0.3,
flux_threshold=0.3,
flux_max=5.0) for f, freq in enumerate(self.frequency)
]
self.skymodel_list = arlexecute.compute(self.skymodel_list, sync=True)
assert isinstance(self.skymodel_list[0].images[0],
Image), self.skymodel_list[0].images[0]
assert isinstance(self.skymodel_list[0].components[0],
Skycomponent), self.skymodel_list[0].components[0]
assert len(self.skymodel_list[0].components) == 119, len(
self.skymodel_list[0].components)
assert len(self.skymodel_list[0].images) == 1, len(
self.skymodel_list[0].images)
assert numpy.max(numpy.abs(
self.skymodel_list[0].images[0].data)) > 0.0, "Image is empty"
self.skymodel_list = arlexecute.scatter(self.skymodel_list)
skymodel_vislist = predict_skymodel_list_arlexecute_workflow(
self.vis_list, self.skymodel_list, context='2d')
skymodel_vislist = arlexecute.compute(skymodel_vislist, sync=True)
assert numpy.max(numpy.abs(skymodel_vislist[0].vis)) > 0.0
def test_predictcal(self):
self.actualSetUp(zerow=True)
future_vis = arlexecute.scatter(self.vis_list[0])
future_skymodel = arlexecute.scatter(self.skymodel_list)
skymodel_vislist = predict_skymodel_list_arlexecute_workflow(future_vis, future_skymodel,
context='2d', docal=True)
skymodel_vislist = arlexecute.compute(skymodel_vislist, sync=True)
vobs = sum_predict_results(skymodel_vislist)
if self.plot:
def plotvis(i, v):
import matplotlib.pyplot as plt
uvr = numpy.hypot(v.u, v.v)
amp = numpy.abs(v.vis[:, 0])
plt.plot(uvr, amp, '.')
plt.title(str(i))
plt.show()
plotvis(0, vobs)
#dict_keys(['facets_wstack', 'facets_timeslice', '2d', 'wstack', 'wprojection', 'timeslice', 'facets', 'wsnapshots'])
print(gcfcf_clipped[1])
contexts = ['2d', 'facets', 'timeslice', 'wstack', 'wprojection']
for context in contexts:
print('Processing context %s' % context)
vtpredict_list =[create_visibility(lowcore, times, frequency, channel_bandwidth=channel_bandwidth,
weight=1.0, phasecentre=phasecentre, polarisation_frame=PolarisationFrame('stokesI'))]
model_list = [model]
vtpredict_list = arlexecute.compute(vtpredict_list, sync=True)
vtpredict_list = arlexecute.scatter(vtpredict_list)
if context == 'wprojection':
future = predict_list_arlexecute_workflow(vtpredict_list, model_list, context='2d', gcfcf=[gcfcf_clipped])
elif context == 'facets':
future = predict_list_arlexecute_workflow(vtpredict_list, model_list, context=context, facets=8)
elif context == 'timeslice':
future = predict_list_arlexecute_workflow(vtpredict_list, model_list, context=context, vis_slices=vis_timeslices(
vtpredict, 'auto'))
elif context == 'wstack':
future = predict_list_arlexecute_workflow(vtpredict_list, model_list, context=context, vis_slices=31)
else:
def test_mpccal_MPCCAL_manysources_subimages(self):
self.actualSetup()
model = create_empty_image_like(self.theta_list[0].image)
if arlexecute.using_dask:
progress = None
else:
progress = self.progress
future_vis = arlexecute.scatter(self.all_skymodel_noniso_vis)
future_model = arlexecute.scatter(model)
future_theta_list = arlexecute.scatter(self.theta_list)
result = mpccal_skymodel_list_arlexecute_workflow(
future_vis,
future_model,
future_theta_list,
mpccal_progress=progress,
nmajor=5,
context='2d',
algorithm='hogbom',
scales=[0, 3, 10],
fractional_threshold=0.3,
threshold=0.2,
gain=0.1,
niter=1000,
psf_support=256,
deconvolve_facets=8,
deconvolve_overlap=8,
deconvolve_taper='tukey')
(self.theta_list, residual) = arlexecute.compute(result, sync=True)
combined_model = calculate_skymodel_equivalent_image(self.theta_list)
psf_obs = invert_list_arlexecute_workflow(
[self.all_skymodel_noniso_vis], [model], context='2d', dopsf=True)
result = restore_list_arlexecute_workflow([combined_model], psf_obs,
[(residual, 0.0)])
result = arlexecute.compute(result, sync=True)
export_image_to_fits(
residual,
arl_path('test_results/test_mpccal_no_edge_residual.fits'))
export_image_to_fits(
result[0],
arl_path('test_results/test_mpccal_no_edge_restored.fits'))
export_image_to_fits(
combined_model,
arl_path('test_results/test_mpccal_no_edge_deconvolved.fits'))
recovered_mpccal_components = find_skycomponents(result[0],
fwhm=2,
threshold=0.32,
npixels=12)
def max_flux(elem):
return numpy.max(elem.flux)
recovered_mpccal_components = sorted(recovered_mpccal_components,
key=max_flux,
reverse=True)
assert recovered_mpccal_components[
0].name == 'Segment 2', recovered_mpccal_components[0].name
assert numpy.abs(recovered_mpccal_components[0].flux[0, 0] - 5.069969928419157) < 1e-7, \
recovered_mpccal_components[0].flux[0, 0]
newscreen = create_empty_image_like(self.screen)
gaintables = [th.gaintable for th in self.theta_list]
newscreen, weights = grid_gaintable_to_screen(
self.all_skymodel_noniso_blockvis, gaintables, newscreen)
export_image_to_fits(
newscreen,
arl_path('test_results/test_mpccal_no_edge_screen.fits'))
export_image_to_fits(
weights,
arl_path('test_results/test_mpccal_no_edge_screenweights.fits'))
arlexecute.close()
def trial_case(results,
seed=180555,
context='wstack',
nworkers=8,
threads_per_worker=1,
memory=8,
processes=True,
order='frequency',
nfreqwin=7,
ntimes=3,
rmax=750.0,
facets=1,
wprojection_planes=1,
use_dask=True,
use_serial_imaging=True,
flux_limit=0.3,
nmajor=5,
dft_threshold=1.0,
use_serial_clean=True,
write_fits=False):
""" Single trial for performance-timings
Simulates visibilities from GLEAM including phase errors
Makes dirty image and PSF
Runs ICAL pipeline
The results are in a dictionary:
'context': input - a string describing concisely the purpose of the test
'time overall', overall execution time (s)
'time predict', time to execute GLEAM prediction graph
'time invert', time to make dirty image
'time invert graph', time to make dirty image graph
'time ICAL graph', time to create ICAL graph
'time ICAL', time to execute ICAL graph
'context', type of imaging e.g. 'wstack'
'nworkers', number of workers to create
'threads_per_worker',
'nnodes', Number of nodes,
'processes', 'order', Ordering of data_models
'nfreqwin', Number of frequency windows in simulation
'ntimes', Number of hour angles in simulation
'rmax', Maximum radius of stations used in simulation (m)
'facets', Number of facets in deconvolution and imaging
'wprojection_planes', Number of wprojection planes
'vis_slices', Number of visibility slices (per Visibbility)
'npixel', Number of pixels in image
'cellsize', Cellsize in radians
'seed', Random number seed
'dirty_max', Maximum in dirty image
'dirty_min', Minimum in dirty image
'restored_max',
'restored_min',
'deconvolved_max',
'deconvolved_min',
'residual_max',
'residual_min',
'git_info', GIT hash (not definitive since local mods are possible)
:param results: Initial state
:param seed: Random number seed (used in gain simulations)
:param context: imaging context
:param context: Type of context: '2d'|'timeslice'|'wstack'
:param nworkers: Number of dask workers to use
:param threads_per_worker: Number of threads per worker
:param processes: Use processes instead of threads 'processes'|'threads'
:param order: See simulate_list_list_arlexecute_workflow_workflowkflow
:param nfreqwin: See simulate_list_list_arlexecute_workflow_workflowkflow
:param ntimes: See simulate_list_list_arlexecute_workflow_workflowkflow
:param rmax: See simulate_list_list_arlexecute_workflow_workflowkflow
:param facets: Number of facets to use
:param wprojection_planes: Number of wprojection planes to use
:param use_dask: Use dask or immediate evaluation
:return: results dictionary
"""
if use_dask:
client = get_dask_Client(threads_per_worker=threads_per_worker,
processes=threads_per_worker == 1,
memory_limit=memory * 1024 * 1024 * 1024,
n_workers=nworkers)
arlexecute.set_client(client)
nodes = findNodes(arlexecute.client)
print("Defined %d workers on %d nodes" % (nworkers, len(nodes)))
print("Workers are: %s" % str(nodes))
else:
arlexecute.set_client(use_dask=use_dask)
results['nnodes'] = 1
def init_logging():
logging.basicConfig(
filename='pipelines_arlexecute_timings.log',
filemode='w',
format='%(asctime)s,%(msecs)d %(name)s %(levelname)s %(message)s',
datefmt='%H:%M:%S',
level=logging.INFO)
init_logging()
log = logging.getLogger()
# Initialise logging on the workers. This appears to only work using the process scheduler.
arlexecute.run(init_logging)
def lprint(*args):
log.info(*args)
print(*args)
lprint("Starting pipelines_arlexecute_timings")
numpy.random.seed(seed)
results['seed'] = seed
start_all = time.time()
results['context'] = context
results['hostname'] = socket.gethostname()
results['git_hash'] = git_hash()
results['epoch'] = time.strftime("%Y-%m-%d %H:%M:%S")
lprint("Context is %s" % context)
results['nworkers'] = nworkers
results['threads_per_worker'] = threads_per_worker
results['processes'] = processes
results['memory'] = memory
results['order'] = order
results['nfreqwin'] = nfreqwin
results['ntimes'] = ntimes
results['rmax'] = rmax
results['facets'] = facets
results['wprojection_planes'] = wprojection_planes
results['dft threshold'] = dft_threshold
results['use_dask'] = use_dask
lprint("At start, configuration is:")
lprint(sort_dict(results))
# Parameters determining scale of simulation.
frequency = numpy.linspace(1.0e8, 1.2e8, nfreqwin)
centre = nfreqwin // 2
if nfreqwin > 1:
channel_bandwidth = numpy.array(nfreqwin *
[frequency[1] - frequency[0]])
else:
channel_bandwidth = numpy.array([1e6])
times = numpy.linspace(-numpy.pi / 4.0, numpy.pi / 4.0, ntimes)
phasecentre = SkyCoord(ra=+0.0 * u.deg,
dec=-40.0 * u.deg,
frame='icrs',
equinox='J2000')
lprint("****** Visibility creation ******")
# Create the empty BlockVisibility's and persist these on the cluster
tmp_bvis_list = simulate_list_arlexecute_workflow(
'LOWBD2',
frequency=frequency,
channel_bandwidth=channel_bandwidth,
times=times,
phasecentre=phasecentre,
order=order,
format='blockvis',
rmax=rmax)
tmp_vis_list = [
arlexecute.execute(convert_blockvisibility_to_visibility)(bv)
for bv in tmp_bvis_list
]
tmp_vis_list = arlexecute.client.compute(tmp_vis_list, sync=True)
vis_list = arlexecute.gather(tmp_vis_list)
import matplotlib.pyplot as plt
plt.clf()
plt.hist(vis_list[0].w, bins=100)
plt.title('Histogram of w samples: rms=%.1f (wavelengths)' %
numpy.std(vis_list[0].w))
plt.xlabel('W (wavelengths)')
plt.show()
plt.clf()
plt.hist(vis_list[0].uvdist, bins=100)
plt.title('Histogram of uvdistance samples')
plt.xlabel('UV Distance (wavelengths)')
plt.show()
arlexecute.client.cancel(tmp_vis_list)
future_vis_list = arlexecute.scatter(vis_list)
# Find the best imaging parameters but don't bring the vis_list back here
print("****** Finding wide field parameters ******")
future_advice = [
arlexecute.execute(advise_wide_field)(
v,
guard_band_image=6.0,
delA=0.1,
facets=facets,
wprojection_planes=wprojection_planes,
oversampling_synthesised_beam=4.0) for v in future_vis_list
]
future_advice = arlexecute.compute(future_advice)
advice = arlexecute.client.gather(future_advice)[-1]
arlexecute.client.cancel(future_advice)
# Deconvolution via sub-images requires 2^n
npixel = advice['npixels2']
results['npixel'] = npixel
cellsize = advice['cellsize']
results['cellsize'] = cellsize
lprint("Image will have %d by %d pixels, cellsize = %.6f rad" %
(npixel, npixel, cellsize))
# Create an empty model image
tmp_model_list = [
arlexecute.execute(create_image)(
npixel=npixel,
cellsize=cellsize,
frequency=[frequency[f]],
channel_bandwidth=[channel_bandwidth[f]],
phasecentre=phasecentre,
polarisation_frame=PolarisationFrame("stokesI"))
for f, freq in enumerate(frequency)
]
model_list = arlexecute.compute(tmp_model_list, sync=True)
future_model_list = arlexecute.scatter(model_list)
lprint("****** Setting up imaging parameters ******")
# Now set up the imaging parameters
template_model = create_image(
npixel=npixel,
cellsize=cellsize,
frequency=[frequency[centre]],
phasecentre=phasecentre,
channel_bandwidth=[channel_bandwidth[centre]],
polarisation_frame=PolarisationFrame("stokesI"))
gcfcf = [create_pswf_convolutionfunction(template_model)]
if context == 'timeslice':
vis_slices = ntimes
lprint("Using timeslice with %d slices" % vis_slices)
elif context == '2d':
vis_slices = 1
elif context == "wprojection":
wstep = advice['wstep']
nw = advice['wprojection_planes']
vis_slices = 1
support = advice['nwpixels']
results['wprojection_planes'] = nw
lprint("****** Starting W projection kernel creation ******")
lprint("Using wprojection with %d planes with wstep %.1f wavelengths" %
(nw, wstep))
lprint("Support of wprojection = %d pixels" % support)
gcfcf = [
create_awterm_convolutionfunction(template_model,
nw=nw,
wstep=wstep,
oversampling=4,
support=support,
use_aaf=True)
]
lprint("Size of W projection gcf, cf = %.2E bytes" % get_size(gcfcf))
else:
context = 'wstack'
vis_slices = advice['vis_slices']
lprint("Using wstack with %d slices" % vis_slices)
gcfcf = arlexecute.scatter(gcfcf, broadcast=True)
results['vis_slices'] = vis_slices
# Make a skymodel from gleam, with bright sources as components and weak sources in an image
lprint("****** Starting GLEAM skymodel creation ******")
future_skymodel_list = [
arlexecute.execute(create_low_test_skymodel_from_gleam)(
npixel=npixel,
cellsize=cellsize,
frequency=[frequency[f]],
phasecentre=phasecentre,
polarisation_frame=PolarisationFrame("stokesI"),
flux_limit=flux_limit,
flux_threshold=dft_threshold,
flux_max=5.0) for f, freq in enumerate(frequency)
]
# We use predict_skymodel so that we can use skycomponents as well as images
lprint("****** Starting GLEAM skymodel prediction ******")
predicted_vis_list = [
predict_skymodel_list_arlexecute_workflow(future_vis_list[f],
[future_skymodel_list[f]],
context=context,
vis_slices=vis_slices,
facets=facets,
gcfcf=gcfcf)[0]
for f, freq in enumerate(frequency)
]
# Corrupt the visibility for the GLEAM model
lprint("****** Visibility corruption ******")
tmp_corrupted_vis_list = corrupt_list_arlexecute_workflow(
predicted_vis_list, phase_error=1.0, seed=seed)
lprint("****** Weighting and tapering ******")
tmp_corrupted_vis_list = weight_list_arlexecute_workflow(
tmp_corrupted_vis_list, future_model_list)
tmp_corrupted_vis_list = taper_list_arlexecute_workflow(
tmp_corrupted_vis_list, 0.003 * 750.0 / rmax)
tmp_corrupted_vis_list = arlexecute.compute(tmp_corrupted_vis_list,
sync=True)
corrupted_vis_list = arlexecute.gather(tmp_corrupted_vis_list)
# arlexecute.client.cancel(predicted_vis_list)
arlexecute.client.cancel(tmp_corrupted_vis_list)
future_corrupted_vis_list = arlexecute.scatter(corrupted_vis_list)
# At this point the only futures are of scatter'ed data so no repeated calculations should be
# incurred.
lprint("****** Starting dirty image calculation ******")
start = time.time()
dirty_list = invert_list_arlexecute_workflow(
future_corrupted_vis_list,
future_model_list,
vis_slices=vis_slices,
context=context,
facets=facets,
use_serial_invert=use_serial_imaging,
gcfcf=gcfcf)
results['size invert graph'] = get_size(dirty_list)
lprint('Size of dirty graph is %.3E bytes' %
(results['size invert graph']))
end = time.time()
results['time invert graph'] = end - start
lprint("Construction of invert graph took %.3f seconds" % (end - start))
start = time.time()
dirty, sumwt = arlexecute.compute(dirty_list, sync=True)[centre]
end = time.time()
results['time invert'] = end - start
lprint("Dirty image invert took %.3f seconds" % (end - start))
lprint("Maximum in dirty image is %f, sumwt is %s" %
(numpy.max(numpy.abs(dirty.data)), str(sumwt)))
qa = qa_image(dirty)
results['dirty_max'] = qa.data['max']
results['dirty_min'] = qa.data['min']
if write_fits:
export_image_to_fits(
dirty, "pipelines_arlexecute_timings-%s-dirty.fits" % context)
lprint("****** Starting prediction ******")
start = time.time()
tmp_vis_list = predict_list_arlexecute_workflow(
future_corrupted_vis_list,
future_model_list,
vis_slices=vis_slices,
context=context,
facets=facets,
use_serial_predict=use_serial_imaging,
gcfcf=gcfcf)
result = arlexecute.compute(tmp_vis_list, sync=True)
# arlexecute.client.cancel(tmp_vis_list)
end = time.time()
results['time predict'] = end - start
lprint("Predict took %.3f seconds" % (end - start))
# Create the ICAL pipeline to run major cycles, starting selfcal at cycle 1. A global solution across all
# frequencies (i.e. Visibilities) is performed.
print("Using subimage clean")
deconvolve_facets = 8
deconvolve_overlap = 16
deconvolve_taper = 'tukey'
lprint("****** Starting ICAL graph creation ******")
controls = create_calibration_controls()
controls['T']['first_selfcal'] = 1
controls['T']['timescale'] = 'auto'
start = time.time()
ical_list = ical_list_arlexecute_workflow(
future_corrupted_vis_list,
model_imagelist=future_model_list,
context=context,
vis_slices=vis_slices,
scales=[0, 3, 10],
algorithm='mmclean',
nmoment=3,
niter=1000,
fractional_threshold=0.1,
threshold=0.01,
nmajor=nmajor,
gain=0.25,
psf_support=64,
deconvolve_facets=deconvolve_facets,
deconvolve_overlap=deconvolve_overlap,
deconvolve_taper=deconvolve_taper,
timeslice='auto',
global_solution=True,
do_selfcal=True,
calibration_context='T',
controls=controls,
use_serial_predict=use_serial_imaging,
use_serial_invert=use_serial_imaging,
use_serial_clean=use_serial_clean,
gcfcf=gcfcf)
results['size ICAL graph'] = get_size(ical_list)
lprint('Size of ICAL graph is %.3E bytes' % results['size ICAL graph'])
end = time.time()
results['time ICAL graph'] = end - start
lprint("Construction of ICAL graph took %.3f seconds" % (end - start))
print("Current objects on cluster: ")
pp.pprint(arlexecute.client.who_has())
#
# Execute the graph
lprint("****** Executing ICAL graph ******")
start = time.time()
deconvolved, residual, restored, gaintables = arlexecute.compute(ical_list,
sync=True)
end = time.time()
results['time ICAL'] = end - start
lprint("ICAL graph execution took %.3f seconds" % (end - start))
qa = qa_image(deconvolved[centre])
results['deconvolved_max'] = qa.data['max']
results['deconvolved_min'] = qa.data['min']
deconvolved_cube = image_gather_channels(deconvolved)
if write_fits:
export_image_to_fits(
deconvolved_cube,
"pipelines_arlexecute_timings-%s-ical_deconvolved.fits" % context)
qa = qa_image(residual[centre][0])
results['residual_max'] = qa.data['max']
results['residual_min'] = qa.data['min']
residual_cube = remove_sumwt(residual)
residual_cube = image_gather_channels(residual_cube)
if write_fits:
export_image_to_fits(
residual_cube,
"pipelines_arlexecute_timings-%s-ical_residual.fits" % context)
qa = qa_image(restored[centre])
results['restored_max'] = qa.data['max']
results['restored_min'] = qa.data['min']
restored_cube = image_gather_channels(restored)
if write_fits:
export_image_to_fits(
restored_cube,
"pipelines_arlexecute_timings-%s-ical_restored.fits" % context)
#
arlexecute.close()
end_all = time.time()
results['time overall'] = end_all - start_all
lprint("At end, results are:")
results = sort_dict(results)
lprint(results)
return results
def actualSetUp(self,
add_errors=False,
freqwin=7,
block=False,
dospectral=True,
dopol=False,
zerow=True):
self.npixel = 256
self.low = create_named_configuration('LOWBD2', rmax=750.0)
self.freqwin = freqwin
self.vis_list = list()
self.ntimes = 5
cellsize = 0.001
self.times = numpy.linspace(-3.0, +3.0, self.ntimes) * numpy.pi / 12.0
self.frequency = numpy.linspace(0.8e8, 1.2e8, self.freqwin)
if freqwin > 1:
self.channelwidth = numpy.array(
freqwin * [self.frequency[1] - self.frequency[0]])
else:
self.channelwidth = numpy.array([1e6])
if dopol:
self.vis_pol = PolarisationFrame('linear')
self.image_pol = PolarisationFrame('stokesIQUV')
f = numpy.array([100.0, 20.0, -10.0, 1.0])
else:
self.vis_pol = PolarisationFrame('stokesI')
self.image_pol = PolarisationFrame('stokesI')
f = numpy.array([100.0])
if dospectral:
flux = numpy.array(
[f * numpy.power(freq / 1e8, -0.7) for freq in self.frequency])
else:
flux = numpy.array([f])
self.phasecentre = SkyCoord(ra=+180.0 * u.deg,
dec=-60.0 * u.deg,
frame='icrs',
equinox='J2000')
self.vis_list = [
arlexecute.execute(ingest_unittest_visibility)(
self.low, [self.frequency[freqwin]],
[self.channelwidth[freqwin]],
self.times,
self.vis_pol,
self.phasecentre,
block=block,
zerow=zerow) for freqwin, _ in enumerate(self.frequency)
]
self.model_imagelist = [
arlexecute.execute(create_unittest_model,
nout=freqwin)(self.vis_list[freqwin],
self.image_pol,
cellsize=cellsize,
npixel=self.npixel)
for freqwin, _ in enumerate(self.frequency)
]
self.componentlist = [
arlexecute.execute(create_unittest_components)(
self.model_imagelist[freqwin],
flux[freqwin, :][numpy.newaxis, :])
for freqwin, _ in enumerate(self.frequency)
]
self.model_imagelist = [
arlexecute.execute(insert_skycomponent,
nout=1)(self.model_imagelist[freqwin],
self.componentlist[freqwin])
for freqwin, _ in enumerate(self.frequency)
]
self.vis_list = [
arlexecute.execute(predict_skycomponent_visibility)(
self.vis_list[freqwin], self.componentlist[freqwin])
for freqwin, _ in enumerate(self.frequency)
]
# Calculate the model convolved with a Gaussian.
self.model_imagelist = arlexecute.compute(self.model_imagelist,
sync=True)
model = self.model_imagelist[0]
self.cmodel = smooth_image(model)
export_image_to_fits(
model,
'%s/test_imaging_arlexecute_deconvolved_model.fits' % self.dir)
export_image_to_fits(
self.cmodel,
'%s/test_imaging_arlexecute_deconvolved_cmodel.fits' % self.dir)
if add_errors and block:
self.vis_list = [
arlexecute.execute(insert_unittest_errors)(self.vis_list[i])
for i, _ in enumerate(self.frequency)
]
# self.vis_list = arlexecute.compute(self.vis_list, sync=True)
self.vis_list = arlexecute.persist(self.vis_list)
self.model_imagelist = arlexecute.scatter(self.model_imagelist)
gleam_model = [arlexecute.execute(create_low_test_image_from_gleam)(npixel=npixel,
frequency=[frequency[f]],
channel_bandwidth=[channel_bandwidth[f]],
cellsize=cellsize,
phasecentre=phasecentre,
polarisation_frame=PolarisationFrame("stokesI"),
flux_limit=1.0,
applybeam=True)
for f, freq in enumerate(frequency)]
print('About to make GLEAM model')
gleam_model = arlexecute.persist(gleam_model)
print('About to run predict to get predicted visibility')
vis_list = arlexecute.scatter(vis_list)
predicted_vislist = predict_list_arlexecute_workflow(vis_list, gleam_model, context='wstack',
vis_slices=vis_slices)
predicted_vislist = arlexecute.persist(predicted_vislist)
corrupted_vislist = corrupt_list_arlexecute_workflow(predicted_vislist, phase_error=1.0)
print('About to run corrupt to get corrupted visibility')
corrupted_vislist = arlexecute.persist(corrupted_vislist)
corrupted_vislist = arlexecute.compute(corrupted_vislist, sync=True)
export_blockvisibility_to_hdf5(corrupted_vislist, 'gleam_simulation_vislist.hdf')
gleam_model = arlexecute.compute(gleam_model, sync=True)
gleam_skymodel = SkyModel(image=gleam_model)
export_skymodel_to_hdf5(gleam_skymodel, 'gleam_simulation_skymodel.hdf')
arlexecute.close()
def actualSetUp(self,
add_errors=False,
nfreqwin=7,
dospectral=True,
dopol=False,
zerow=True):
self.npixel = 512
self.low = create_named_configuration('LOWBD2', rmax=750.0)
self.freqwin = nfreqwin
self.vis_list = list()
self.ntimes = 5
self.times = numpy.linspace(-3.0, +3.0, self.ntimes) * numpy.pi / 12.0
self.frequency = numpy.linspace(0.8e8, 1.2e8, self.freqwin)
if self.freqwin > 1:
self.channelwidth = numpy.array(
self.freqwin * [self.frequency[1] - self.frequency[0]])
else:
self.channelwidth = numpy.array([1e6])
if dopol:
self.vis_pol = PolarisationFrame('linear')
self.image_pol = PolarisationFrame('stokesIQUV')
f = numpy.array([100.0, 20.0, -10.0, 1.0])
else:
self.vis_pol = PolarisationFrame('stokesI')
self.image_pol = PolarisationFrame('stokesI')
f = numpy.array([100.0])
if dospectral:
flux = numpy.array(
[f * numpy.power(freq / 1e8, -0.7) for freq in self.frequency])
else:
flux = numpy.array([f])
self.phasecentre = SkyCoord(ra=+180.0 * u.deg,
dec=-60.0 * u.deg,
frame='icrs',
equinox='J2000')
self.blockvis_list = [
arlexecute.execute(ingest_unittest_visibility,
nout=1)(self.low, [self.frequency[i]],
[self.channelwidth[i]],
self.times,
self.vis_pol,
self.phasecentre,
block=True,
zerow=zerow) for i in range(nfreqwin)
]
self.blockvis_list = arlexecute.compute(self.blockvis_list, sync=True)
self.blockvis_list = arlexecute.scatter(self.blockvis_list)
self.vis_list = [
arlexecute.execute(convert_blockvisibility_to_visibility,
nout=1)(bv) for bv in self.blockvis_list
]
self.vis_list = arlexecute.compute(self.vis_list, sync=True)
self.vis_list = arlexecute.scatter(self.vis_list)
self.model_imagelist = [
arlexecute.execute(create_unittest_model,
nout=1)(self.vis_list[i],
self.image_pol,
npixel=self.npixel,
cellsize=0.0005)
for i in range(nfreqwin)
]
self.model_imagelist = arlexecute.compute(self.model_imagelist,
sync=True)
self.model_imagelist = arlexecute.scatter(self.model_imagelist)
self.components_list = [
arlexecute.execute(create_unittest_components)(
self.model_imagelist[freqwin],
flux[freqwin, :][numpy.newaxis, :])
for freqwin, m in enumerate(self.model_imagelist)
]
self.components_list = arlexecute.compute(self.components_list,
sync=True)
self.components_list = arlexecute.scatter(self.components_list)
self.blockvis_list = [
arlexecute.execute(predict_skycomponent_visibility)(
self.blockvis_list[freqwin], self.components_list[freqwin])
for freqwin, _ in enumerate(self.blockvis_list)
]
self.blockvis_list = arlexecute.compute(self.blockvis_list, sync=True)
self.vis = self.blockvis_list[0]
self.blockvis_list = arlexecute.scatter(self.blockvis_list)
self.model_imagelist = [
arlexecute.execute(insert_skycomponent,
nout=1)(self.model_imagelist[freqwin],
self.components_list[freqwin])
for freqwin in range(nfreqwin)
]
self.model_imagelist = arlexecute.compute(self.model_imagelist,
sync=True)
model = self.model_imagelist[0]
self.cmodel = smooth_image(model)
if self.persist:
export_image_to_fits(
model, '%s/test_pipelines_arlexecute_model.fits' % self.dir)
export_image_to_fits(
self.cmodel,
'%s/test_pipelines_arlexecute_cmodel.fits' % self.dir)
if add_errors:
gt = create_gaintable_from_blockvisibility(self.vis)
gt = simulate_gaintable(gt,
phase_error=0.1,
amplitude_error=0.0,
smooth_channels=1,
leakage=0.0,
seed=180555)
self.blockvis_list = [
arlexecute.execute(apply_gaintable,
nout=1)(self.blockvis_list[i], gt)
for i in range(self.freqwin)
]
self.blockvis_list = arlexecute.compute(self.blockvis_list,
sync=True)
self.blockvis_list = arlexecute.scatter(self.blockvis_list)
self.vis_list = [
arlexecute.execute(convert_blockvisibility_to_visibility)(bv)
for bv in self.blockvis_list
]
self.vis_list = arlexecute.compute(self.vis_list, sync=True)
self.vis_list = arlexecute.scatter(self.vis_list)
self.model_imagelist = [
arlexecute.execute(create_unittest_model,
nout=1)(self.vis_list[i],
self.image_pol,
npixel=self.npixel,
cellsize=0.0005)
for i in range(nfreqwin)
]
self.model_imagelist = arlexecute.compute(self.model_imagelist,
sync=True)
self.model_imagelist = arlexecute.scatter(self.model_imagelist)
controls = create_calibration_controls()
controls['T']['first_selfcal'] = 1
controls['G']['first_selfcal'] = 3
controls['B']['first_selfcal'] = 4
controls['T']['timescale'] = 'auto'
controls['G']['timescale'] = 'auto'
controls['B']['timescale'] = 1e5
pp.pprint(controls)
# In[ ]:
future_vislist = arlexecute.scatter(vislist)
ntimes = len(vislist[0].time)
ical_list = ical_list_arlexecute_workflow(future_vislist,
model_imagelist=model_list,
context='wstack',
calibration_context='TG',
controls=controls,
scales=[0, 3, 10],
algorithm='mmclean',
nmoment=3,
niter=1000,
fractional_threshold=0.1,
threshold=0.1,
nmajor=5,
gain=0.25,
deconvolve_facets=8,
def trial_case(results, seed=180555, context='wstack', nworkers=8, threads_per_worker=1, memory=8,
processes=True, order='frequency', nfreqwin=7, ntimes=3, rmax=750.0,
facets=1, wprojection_planes=1, use_dask=True, use_serial_imaging=False,
flux_limit=0.3, nmajor=5, dft_threshold=1.0):
""" Single trial for performance-timings
Simulates visibilities from GLEAM including phase errors
Makes dirty image and PSF
Runs ICAL pipeline
The results are in a dictionary:
'context': input - a string describing concisely the purpose of the test
'time overall', overall execution time (s)
'time create gleam', time to create GLEAM prediction graph
'time predict', time to execute GLEAM prediction graph
'time corrupt', time to corrupt data_models
'time invert', time to make dirty image
'time psf invert', time to make PSF
'time ICAL graph', time to create ICAL graph
'time ICAL', time to execute ICAL graph
'context', type of imaging e.g. 'wstack'
'nworkers', number of workers to create
'threads_per_worker',
'nnodes', Number of nodes,
'processes', 'order', Ordering of data_models
'nfreqwin', Number of frequency windows in simulation
'ntimes', Number of hour angles in simulation
'rmax', Maximum radius of stations used in simulation (m)
'facets', Number of facets in deconvolution and imaging
'wprojection_planes', Number of wprojection planes
'vis_slices', Number of visibility slices (per Visibbility)
'npixel', Number of pixels in image
'cellsize', Cellsize in radians
'seed', Random number seed
'dirty_max', Maximum in dirty image
'dirty_min', Minimum in dirty image
'psf_max',
'psf_min',
'restored_max',
'restored_min',
'deconvolved_max',
'deconvolved_min',
'residual_max',
'residual_min',
'git_info', GIT hash (not definitive since local mods are possible)
:param results: Initial state
:param seed: Random number seed (used in gain simulations)
:param context: imaging context
:param context: Type of context: '2d'|'timeslice'|'wstack'
:param nworkers: Number of dask workers to use
:param threads_per_worker: Number of threads per worker
:param processes: Use processes instead of threads 'processes'|'threads'
:param order: See simulate_list_list_arlexecute_workflow_workflowkflow
:param nfreqwin: See simulate_list_list_arlexecute_workflow_workflowkflow
:param ntimes: See simulate_list_list_arlexecute_workflow_workflowkflow
:param rmax: See simulate_list_list_arlexecute_workflow_workflowkflow
:param facets: Number of facets to use
:param wprojection_planes: Number of wprojection planes to use
:param use_dask: Use dask or immediate evaluation
:return: results dictionary
"""
if use_dask:
client = get_dask_Client(threads_per_worker=threads_per_worker,
processes = threads_per_worker == 1,
memory_limit=memory * 1024 * 1024 * 1024,
n_workers=nworkers)
arlexecute.set_client(client)
nodes = findNodes(arlexecute.client)
print("Defined %d workers on %d nodes" % (nworkers, len(nodes)))
print("Workers are: %s" % str(nodes))
else:
arlexecute.set_client(use_dask=use_dask)
results['nnodes'] = 1
def init_logging():
logging.basicConfig(filename='pipelines-arlexecute-timings.log',
filemode='a',
format='%(asctime)s,%(msecs)d %(name)s %(levelname)s %(message)s',
datefmt='%H:%M:%S',
level=logging.INFO)
init_logging()
log = logging.getLogger()
# Initialise logging on the workers. This appears to only work using the process scheduler.
arlexecute.run(init_logging)
def lprint(s):
log.info(s)
print(s)
lprint("Starting pipelines-arlexecute-timings")
numpy.random.seed(seed)
results['seed'] = seed
start_all = time.time()
results['context'] = context
results['hostname'] = socket.gethostname()
results['git_hash'] = git_hash()
results['epoch'] = time.strftime("%Y-%m-%d %H:%M:%S")
lprint("Context is %s" % context)
results['nworkers'] = nworkers
results['threads_per_worker'] = threads_per_worker
results['processes'] = processes
results['memory'] = memory
results['order'] = order
results['nfreqwin'] = nfreqwin
results['ntimes'] = ntimes
results['rmax'] = rmax
results['facets'] = facets
results['wprojection_planes'] = wprojection_planes
results['dft threshold'] = dft_threshold
results['use_dask'] = use_dask
lprint("At start, configuration is:")
lprint(results)
# Parameters determining scale
frequency = numpy.linspace(1.0e8, 1.2e8, nfreqwin)
centre = nfreqwin // 2
if nfreqwin > 1:
channel_bandwidth = numpy.array(nfreqwin * [frequency[1] - frequency[0]])
else:
channel_bandwidth = numpy.array([1e6])
times = numpy.linspace(-numpy.pi / 4.0, numpy.pi / 4.0, ntimes)
phasecentre = SkyCoord(ra=+30.0 * u.deg, dec=-60.0 * u.deg, frame='icrs', equinox='J2000')
bvis_list = simulate_list_arlexecute_workflow('LOWBD2',
frequency=frequency,
channel_bandwidth=channel_bandwidth,
times=times,
phasecentre=phasecentre,
order=order,
format='blockvis',
rmax=rmax)
lprint("****** Visibility creation ******")
bvis_list = arlexecute.compute(bvis_list, sync=True)
vis_list = [arlexecute.execute(convert_blockvisibility_to_visibility(bv)) for bv in bvis_list]
vis_list = arlexecute.compute(vis_list, sync=True)
# Find the best imaging parameters but don't bring the vis_list back here
def get_wf(v):
return advise_wide_field(v, guard_band_image=6.0,
delA=0.1,
facets=facets,
wprojection_planes=wprojection_planes,
oversampling_synthesised_beam=4.0)
advice = arlexecute.compute(arlexecute.execute(get_wf)(vis_list[-1]), sync=True)
# Deconvolution via sub-images requires 2^n
npixel = advice['npixels2']
results['npixel'] = npixel
cellsize = advice['cellsize']
results['cellsize'] = cellsize
lprint("Image will have %d by %d pixels, cellsize = %.6f rad" % (npixel, npixel, cellsize))
# Create an empty model image
model_list = [arlexecute.execute(create_image_from_visibility)
(vis_list[f],
npixel=npixel, cellsize=cellsize,
frequency=[frequency[f]],
channel_bandwidth=[channel_bandwidth[f]],
polarisation_frame=PolarisationFrame("stokesI"))
for f, freq in enumerate(frequency)]
model_list = arlexecute.compute(model_list, sync=True)
model_list = arlexecute.scatter(model_list)
start = time.time()
vis_list = weight_list_arlexecute_workflow(vis_list, model_list)
vis_list = taper_list_arlexecute_workflow(vis_list, 0.003 * 750.0 / rmax)
print("****** Starting weighting and tapering ******")
vis_list = arlexecute.compute(vis_list, sync=True)
end = time.time()
results['time weight'] = end - start
print("Weighting took %.3f seconds" % (end - start))
vis_list = arlexecute.scatter(vis_list)
# Now set up the imaging parameters
gcfcf_list = [None for i in range(nfreqwin)]
if context == 'timeslice':
vis_slices = ntimes
lprint("Using timeslice with %d slices" % vis_slices)
elif context == '2d':
vis_slices = 1
elif context == "wprojection":
wstep = advice['wstep']
nw = advice['wprojection_planes']
vis_slices = 1
support = advice['nwpixels']
results['wprojection_planes'] = nw
lprint("Using wprojection with %d planes with wstep %.1f wavelengths" % (nw, wstep))
start = time.time()
lprint("****** Starting W projection kernel creation ******")
gcfcf_list = [arlexecute.execute(create_awterm_convolutionfunction, nout=1)
(m, nw=nw, wstep=wstep, oversampling=8, support=support, use_aaf=True)
for m in model_list]
gcfcf_list = arlexecute.compute(gcfcf_list, sync=True)
end = time.time()
results['time create wprojection'] = end - start
lprint("Creating W projection kernel took %.3f seconds" % (end - start))
cf_image = convert_convolutionfunction_to_image(gcfcf_list[centre][1])
cf_image.data = numpy.real(cf_image.data)
export_image_to_fits(cf_image, "pipelines-arlexecute-timings-wterm-cf.fits")
gcfcf_list = arlexecute.scatter(gcfcf_list)
else:
context = 'wstack'
vis_slices = advice['vis_slices']
lprint("Using wstack with %d slices" % vis_slices)
results['vis_slices'] = vis_slices
# Make a skymodel from gleam, with bright sources as components and weak sources in an image
lprint("****** Starting GLEAM skymodel creation ******")
start = time.time()
skymodel_list = [arlexecute.execute(create_low_test_skymodel_from_gleam)
(npixel=npixel, cellsize=cellsize, frequency=[frequency[f]],
phasecentre=phasecentre,
polarisation_frame=PolarisationFrame("stokesI"),
flux_limit=flux_limit,
flux_threshold=dft_threshold,
flux_max=5.0) for f, freq in enumerate(frequency)]
skymodel_list = arlexecute.compute(skymodel_list, sync=True)
end = time.time()
lprint("GLEAM skymodel creation took %.3f seconds" % (end - start))
results['time create gleam'] = end - start
lprint("****** Starting GLEAM skymodel prediction ******")
start = time.time()
predicted_vis_list = [predict_skymodel_list_arlexecute_workflow(vis_list[f], [skymodel_list[f]], context=context,
vis_slices=vis_slices, facets=facets,
gcfcf=[gcfcf_list[f]])[0]
for f, freq in enumerate(frequency)]
predicted_vis_list = arlexecute.compute(predicted_vis_list, sync=True)
end = time.time()
lprint("GLEAM skymodel prediction took %.3f seconds" % (end - start))
results['time predict gleam'] = end - start
lprint("****** Starting psf image calculation ******")
start = time.time()
predicted_vis_list = arlexecute.scatter(predicted_vis_list)
psf_list = invert_list_arlexecute_workflow(predicted_vis_list, model_list, vis_slices=vis_slices,
dopsf=True, context=context, facets=facets,
use_serial_invert=use_serial_imaging, gcfcf=gcfcf_list)
psf, sumwt = arlexecute.compute(psf_list, sync=True)[centre]
end = time.time()
results['time psf invert'] = end - start
lprint("PSF invert took %.3f seconds" % (end - start))
lprint("Maximum in psf image is %f, sumwt is %s" % (numpy.max(numpy.abs(psf.data)), str(sumwt)))
qa = qa_image(psf)
results['psf_max'] = qa.data['max']
results['psf_min'] = qa.data['min']
export_image_to_fits(psf, "pipelines-arlexecute-timings-%s-psf.fits" % context)
# Make a smoothed model image for comparison
# smoothed_model_list = restore_list_arlexecute_workflow(gleam_model_list, psf_list)
# smoothed_model_list = arlexecute.compute(smoothed_model_list, sync=True)
# smoothed_cube = image_gather_channels(smoothed_model_list)
# export_image_to_fits(smoothed_cube, "pipelines-arlexecute-timings-cmodel.fits")
# Create an empty model image
model_list = [arlexecute.execute(create_image_from_visibility)
(predicted_vis_list[f],
npixel=npixel, cellsize=cellsize,
frequency=[frequency[f]],
channel_bandwidth=[channel_bandwidth[f]],
polarisation_frame=PolarisationFrame("stokesI"))
for f, freq in enumerate(frequency)]
model_list = arlexecute.compute(model_list, sync=True)
model_list = arlexecute.scatter(model_list)
lprint("****** Starting dirty image calculation ******")
start = time.time()
dirty_list = invert_list_arlexecute_workflow(predicted_vis_list, model_list, vis_slices=vis_slices,
context=context, facets=facets,
use_serial_invert=use_serial_imaging, gcfcf=gcfcf_list)
dirty, sumwt = arlexecute.compute(dirty_list, sync=True)[centre]
end = time.time()
results['time invert'] = end - start
lprint("Dirty image invert took %.3f seconds" % (end - start))
lprint("Maximum in dirty image is %f, sumwt is %s" % (numpy.max(numpy.abs(dirty.data)), str(sumwt)))
qa = qa_image(dirty)
results['dirty_max'] = qa.data['max']
results['dirty_min'] = qa.data['min']
export_image_to_fits(dirty, "pipelines-arlexecute-timings-%s-dirty.fits" % context)
# Corrupt the visibility for the GLEAM model
lprint("****** Visibility corruption ******")
start = time.time()
corrupted_vis_list = corrupt_list_arlexecute_workflow(predicted_vis_list, phase_error=1.0, seed=seed)
corrupted_vis_list = arlexecute.compute(corrupted_vis_list, sync=True)
end = time.time()
results['time corrupt'] = end - start
lprint("Visibility corruption took %.3f seconds" % (end - start))
# Create the ICAL pipeline to run major cycles, starting selfcal at cycle 1. A global solution across all
# frequencies (i.e. Visibilities) is performed.
lprint("****** Starting ICAL ******")
controls = create_calibration_controls()
controls['T']['first_selfcal'] = 1
controls['T']['timescale'] = 'auto'
start = time.time()
ical_list = ical_list_arlexecute_workflow(corrupted_vis_list,
model_imagelist=model_list,
context=context,
vis_slices=vis_slices,
scales=[0, 3, 10],
algorithm='mmclean',
nmoment=3, niter=1000,
fractional_threshold=0.1,
threshold=0.01, nmajor=nmajor,
gain=0.25,
psf_support=64,
deconvolve_facets=8,
deconvolve_overlap=32,
deconvolve_taper='tukey',
timeslice='auto',
global_solution=True,
do_selfcal=True,
calibration_context='T',
controls=controls,
use_serial_predict=use_serial_imaging,
use_serial_invert=use_serial_imaging,
gcfcf=gcfcf_list)
end = time.time()
results['time ICAL graph'] = end - start
lprint("Construction of ICAL graph took %.3f seconds" % (end - start))
# Execute the graph
start = time.time()
result = arlexecute.compute(ical_list, sync=True)
deconvolved, residual, restored, gaintables = result
end = time.time()
results['time ICAL'] = end - start
lprint("ICAL graph execution took %.3f seconds" % (end - start))
qa = qa_image(deconvolved[centre])
results['deconvolved_max'] = qa.data['max']
results['deconvolved_min'] = qa.data['min']
deconvolved_cube = image_gather_channels(deconvolved)
export_image_to_fits(deconvolved_cube, "pipelines-arlexecute-timings-%s-ical_deconvolved.fits" % context)
qa = qa_image(residual[centre][0])
results['residual_max'] = qa.data['max']
results['residual_min'] = qa.data['min']
residual_cube = remove_sumwt(residual)
residual_cube = image_gather_channels(residual_cube)
export_image_to_fits(residual_cube, "pipelines-arlexecute-timings-%s-ical_residual.fits" % context)
qa = qa_image(restored[centre])
results['restored_max'] = qa.data['max']
results['restored_min'] = qa.data['min']
restored_cube = image_gather_channels(restored)
export_image_to_fits(restored_cube, "pipelines-arlexecute-timings-%s-ical_restored.fits" % context)
#
arlexecute.close()
end_all = time.time()
results['time overall'] = end_all - start_all
lprint("At end, results are:")
lprint(results)
return results
print('Reading visibilities')
vis_list = arlexecute.compute(vis_list, sync=True)
cellsize = 0.001
npixel = 1024
pol_frame = PolarisationFrame("stokesI")
model_list = [arlexecute.execute(create_image_from_visibility)(v, npixel=npixel, cellsize=cellsize,
polarisation_frame=pol_frame)
for v in vis_list]
print('Creating model images')
model_list = arlexecute.compute(model_list, sync=True)
print('Creating graph')
future_vis_list = arlexecute.scatter(vis_list)
future_model_list = arlexecute.scatter(model_list)
controls = create_calibration_controls()
controls['T']['first_selfcal'] = 1
controls['G']['first_selfcal'] = 3
controls['B']['first_selfcal'] = 4
controls['T']['timescale'] = 'auto'
controls['G']['timescale'] = 'auto'
controls['B']['timescale'] = 1e5
ical_list = ical_list_arlexecute_workflow(future_vis_list,
model_imagelist=future_model_list,
context='wstack', vis_slices=51,
def trial_case(results,
seed=180555,
context='wstack',
nworkers=8,
threads_per_worker=1,
memory=8,
processes=True,
order='frequency',
nfreqwin=7,
ntimes=3,
rmax=750.0,
facets=1,
wprojection_planes=1,
use_dask=True,
use_serial=False):
""" Single trial for performance-timings
Simulates visibilities from GLEAM including phase errors
Makes dirty image and PSF
Runs ICAL pipeline
The results are in a dictionary:
'context': input - a string describing concisely the purpose of the test
'time overall', overall execution time (s)
'time create gleam', time to create GLEAM prediction graph
'time predict', time to execute GLEAM prediction graph
'time corrupt', time to corrupt data_models
'time invert', time to make dirty image
'time psf invert', time to make PSF
'time ICAL graph', time to create ICAL graph
'time ICAL', time to execute ICAL graph
'context', type of imaging e.g. 'wstack'
'nworkers', number of workers to create
'threads_per_worker',
'nnodes', Number of nodes,
'processes', 'order', Ordering of data_models
'nfreqwin', Number of frequency windows in simulation
'ntimes', Number of hour angles in simulation
'rmax', Maximum radius of stations used in simulation (m)
'facets', Number of facets in deconvolution and imaging
'wprojection_planes', Number of wprojection planes
'vis_slices', Number of visibility slices (per Visibbility)
'npixel', Number of pixels in image
'cellsize', Cellsize in radians
'seed', Random number seed
'dirty_max', Maximum in dirty image
'dirty_min', Minimum in dirty image
'psf_max',
'psf_min',
'restored_max',
'restored_min',
'deconvolved_max',
'deconvolved_min',
'residual_max',
'residual_min',
'git_info', GIT hash (not definitive since local mods are possible)
:param results: Initial state
:param seed: Random number seed (used in gain simulations)
:param context: imaging context
:param context: Type of context: '2d'|'timeslice'|'wstack'
:param nworkers: Number of dask workers to use
:param threads_per_worker: Number of threads per worker
:param processes: Use processes instead of threads 'processes'|'threads'
:param order: See simulate_list_list_arlexecute_workflow_workflowkflow
:param nfreqwin: See simulate_list_list_arlexecute_workflow_workflowkflow
:param ntimes: See simulate_list_list_arlexecute_workflow_workflowkflow
:param rmax: See simulate_list_list_arlexecute_workflow_workflowkflow
:param facets: Number of facets to use
:param wprojection_planes: Number of wprojection planes to use
:param use_dask: Use dask or immediate evaluation
:param kwargs:
:return: results dictionary
"""
numpy.random.seed(seed)
results['seed'] = seed
start_all = time.time()
results['context'] = context
results['hostname'] = socket.gethostname()
results['git_hash'] = git_hash()
results['epoch'] = time.strftime("%Y-%m-%d %H:%M:%S")
zerow = False
print("Context is %s" % context)
results['nworkers'] = nworkers
results['threads_per_worker'] = threads_per_worker
results['processes'] = processes
results['memory'] = memory
results['order'] = order
results['nfreqwin'] = nfreqwin
results['ntimes'] = ntimes
results['rmax'] = rmax
results['facets'] = facets
results['wprojection_planes'] = wprojection_planes
results['use_dask'] = use_dask
print("At start, configuration is {0!r}".format(results))
# Parameters determining scale
frequency = numpy.linspace(0.8e8, 1.2e8, nfreqwin)
centre = nfreqwin // 2
if nfreqwin > 1:
channel_bandwidth = numpy.array(nfreqwin *
[frequency[1] - frequency[0]])
else:
channel_bandwidth = numpy.array([1e6])
times = numpy.linspace(-numpy.pi / 3.0, numpy.pi / 3.0, ntimes)
phasecentre = SkyCoord(ra=+30.0 * u.deg,
dec=-60.0 * u.deg,
frame='icrs',
equinox='J2000')
if use_dask:
client = get_dask_Client(threads_per_worker=threads_per_worker,
memory_limit=memory * 1024 * 1024 * 1024,
n_workers=nworkers)
arlexecute.set_client(client)
nodes = findNodes(arlexecute.client)
unodes = list(numpy.unique(nodes))
results['nnodes'] = len(unodes)
print("Defined %d workers on %d nodes" % (nworkers, results['nnodes']))
print("Workers are: %s" % str(nodes))
else:
arlexecute.set_client(use_dask=use_dask)
results['nnodes'] = 1
unodes = None
vis_list = simulate_list_arlexecute_workflow(
'LOWBD2',
frequency=frequency,
channel_bandwidth=channel_bandwidth,
times=times,
phasecentre=phasecentre,
order=order,
format='blockvis',
rmax=rmax)
print("****** Visibility creation ******")
vis_list = arlexecute.persist(vis_list)
# Find the best imaging parameters but don't bring the vis_list back here
def get_wf(bv):
v = convert_blockvisibility_to_visibility(bv)
return advise_wide_field(v,
guard_band_image=6.0,
delA=0.02,
facets=facets,
wprojection_planes=wprojection_planes,
oversampling_synthesised_beam=4.0)
wprojection_planes = 1
advice = arlexecute.compute(arlexecute.execute(get_wf)(vis_list[0]),
sync=True)
npixel = advice['npixels2']
cellsize = advice['cellsize']
if context == 'timeslice':
vis_slices = ntimes
print("Using timeslice with %d slices" % vis_slices)
elif context == '2d':
vis_slices = 1
else:
context = 'wstack'
vis_slices = 5 * advice['vis_slices']
print("Using wstack with %d slices" % vis_slices)
results['vis_slices'] = vis_slices
results['cellsize'] = cellsize
results['npixel'] = npixel
gleam_model_list = [
arlexecute.execute(create_low_test_image_from_gleam)(
npixel=npixel,
frequency=[frequency[f]],
channel_bandwidth=[channel_bandwidth[f]],
cellsize=cellsize,
phasecentre=phasecentre,
polarisation_frame=PolarisationFrame("stokesI"),
flux_limit=0.3,
applybeam=True) for f, freq in enumerate(frequency)
]
start = time.time()
print("****** Starting GLEAM model creation ******")
gleam_model_list = arlexecute.compute(gleam_model_list, sync=True)
cmodel = smooth_image(gleam_model_list[centre])
export_image_to_fits(cmodel,
"pipelines-timings-arlexecute-gleam_cmodel.fits")
end = time.time()
results['time create gleam'] = end - start
print("Creating GLEAM model took %.2f seconds" % (end - start))
gleam_model_list = arlexecute.scatter(gleam_model_list)
vis_list = predict_list_arlexecute_workflow(vis_list,
gleam_model_list,
vis_slices=vis_slices,
context=context)
start = time.time()
print("****** Starting GLEAM model visibility prediction ******")
vis_list = arlexecute.compute(vis_list, sync=True)
end = time.time()
results['time predict'] = end - start
print("GLEAM model Visibility prediction took %.2f seconds" %
(end - start))
# Corrupt the visibility for the GLEAM model
print("****** Visibility corruption ******")
vis_list = corrupt_list_arlexecute_workflow(vis_list, phase_error=1.0)
start = time.time()
vis_list = arlexecute.compute(vis_list, sync=True)
vis_list = arlexecute.scatter(vis_list)
end = time.time()
results['time corrupt'] = end - start
print("Visibility corruption took %.2f seconds" % (end - start))
# Create an empty model image
model_list = [
arlexecute.execute(create_image_from_visibility)(
vis_list[f],
npixel=npixel,
cellsize=cellsize,
frequency=[frequency[f]],
channel_bandwidth=[channel_bandwidth[f]],
polarisation_frame=PolarisationFrame("stokesI"))
for f, freq in enumerate(frequency)
]
model_list = arlexecute.compute(model_list, sync=True)
model_list = arlexecute.scatter(model_list)
psf_list = invert_list_arlexecute_workflow(vis_list,
model_list,
vis_slices=vis_slices,
context=context,
facets=facets,
dopsf=True)
start = time.time()
print("****** Starting PSF calculation ******")
psf, sumwt = arlexecute.compute(psf_list, sync=True)[centre]
end = time.time()
results['time psf invert'] = end - start
print("PSF invert took %.2f seconds" % (end - start))
results['psf_max'] = qa_image(psf).data['max']
results['psf_min'] = qa_image(psf).data['min']
dirty_list = invert_list_arlexecute_workflow(vis_list,
model_list,
vis_slices=vis_slices,
context=context,
facets=facets)
start = time.time()
print("****** Starting dirty image calculation ******")
dirty, sumwt = arlexecute.compute(dirty_list, sync=True)[centre]
end = time.time()
results['time invert'] = end - start
print("Dirty image invert took %.2f seconds" % (end - start))
print("Maximum in dirty image is ", numpy.max(numpy.abs(dirty.data)),
", sumwt is ", sumwt)
qa = qa_image(dirty)
results['dirty_max'] = qa.data['max']
results['dirty_min'] = qa.data['min']
# Create the ICAL pipeline to run 5 major cycles, starting selfcal at cycle 1. A global solution across all
# frequencies (i.e. Visibilities) is performed.
start = time.time()
print("****** Starting ICAL ******")
controls = create_calibration_controls()
controls['T']['first_selfcal'] = 1
controls['G']['first_selfcal'] = 3
controls['B']['first_selfcal'] = 4
controls['T']['timescale'] = 'auto'
controls['G']['timescale'] = 'auto'
controls['B']['timescale'] = 1e5
if nfreqwin > 6:
nmoment = 3
algorithm = 'mmclean'
elif nfreqwin > 2:
nmoment = 2
algorithm = 'mmclean'
else:
nmoment = 1
algorithm = 'msclean'
start = time.time()
ical_list = ical_list_arlexecute_workflow(vis_list,
model_imagelist=model_list,
context='wstack',
calibration_context='TG',
controls=controls,
scales=[0, 3, 10],
algorithm=algorithm,
nmoment=nmoment,
niter=1000,
fractional_threshold=0.1,
threshold=0.1,
nmajor=5,
gain=0.25,
vis_slices=vis_slices,
timeslice='auto',
global_solution=False,
psf_support=64,
do_selfcal=True)
end = time.time()
results['time ICAL graph'] = end - start
print("Construction of ICAL graph took %.2f seconds" % (end - start))
# Execute the graph
start = time.time()
result = arlexecute.compute(ical_list, sync=True)
deconvolved, residual, restored = result
end = time.time()
results['time ICAL'] = end - start
print("ICAL graph execution took %.2f seconds" % (end - start))
qa = qa_image(deconvolved[centre])
results['deconvolved_max'] = qa.data['max']
results['deconvolved_min'] = qa.data['min']
export_image_to_fits(deconvolved[centre],
"pipelines-timings-arlexecute-ical_deconvolved.fits")
qa = qa_image(residual[centre][0])
results['residual_max'] = qa.data['max']
results['residual_min'] = qa.data['min']
export_image_to_fits(residual[centre][0],
"pipelines-timings-arlexecute-ical_residual.fits")
qa = qa_image(restored[centre])
results['restored_max'] = qa.data['max']
results['restored_min'] = qa.data['min']
export_image_to_fits(restored[centre],
"pipelines-timings-arlexecute-ical_restored.fits")
#
arlexecute.close()
end_all = time.time()
results['time overall'] = end_all - start_all
print("At end, results are {0!r}".format(results))
return results
# In[6]:
gleam_model = [
arlexecute.execute(create_low_test_image_from_gleam)(
npixel=npixel,
frequency=[frequency[f]],
channel_bandwidth=[channel_bandwidth[f]],
cellsize=cellsize,
phasecentre=phasecentre,
polarisation_frame=PolarisationFrame("stokesI"),
flux_limit=1.0,
applybeam=True) for f, freq in enumerate(frequency)
]
log.info('About to make GLEAM model')
gleam_model = arlexecute.compute(gleam_model, sync=True)
future_gleam_model = arlexecute.scatter(gleam_model)
# In[7]:
log.info('About to run predict to get predicted visibility')
start = time.time()
future_vis_graph = arlexecute.scatter(vis_list)
predicted_vislist = predict_list_arlexecute_workflow(future_vis_graph,
gleam_model,
context='wstack',
vis_slices=vis_slices)
predicted_vislist = arlexecute.compute(predicted_vislist, sync=True)
end = time.time()
corrupted_vislist = corrupt_list_arlexecute_workflow(predicted_vislist,
phase_error=1.0)
log.info('About to run corrupt to get corrupted visibility')
gleam_model = [
arlexecute.execute(create_low_test_image_from_gleam)(
npixel=npixel,
frequency=[frequency[f]],
channel_bandwidth=[channel_bandwidth[f]],
cellsize=cellsize,
phasecentre=phasecentre,
polarisation_frame=PolarisationFrame("stokesI"),
flux_limit=1.0,
applybeam=True) for f, freq in enumerate(frequency)
]
log.info('About to make GLEAM model')
gleam_model = arlexecute.compute(gleam_model, sync=True)
gleam_skymodel = SkyModel(images=gleam_model)
export_skymodel_to_hdf5(gleam_skymodel, 'gleam_simulation_skymodel.hdf')
future_gleam_model = arlexecute.scatter(gleam_model)
# In[ ]:
log.info('About to run predict to get predicted visibility')
future_vis_graph = arlexecute.scatter(vis_list)
predicted_vislist = predict_list_arlexecute_workflow(future_vis_graph,
gleam_model,
context='wstack',
vis_slices=vis_slices)
corrupted_vislist = corrupt_list_arlexecute_workflow(predicted_vislist,
phase_error=1.0)
log.info('About to run corrupt to get corrupted visibility')
corrupted_vislist = arlexecute.compute(corrupted_vislist, sync=True)
export_blockvisibility_to_hdf5(corrupted_vislist,
screen)
all_skymodel = [
SkyModel(components=[all_components[i]], gaintable=all_gaintables[i])
for i, sm in enumerate(all_components)
]
#######################################################################################################
# Calculate visibility by using the predict_skymodel function which applies a different gaintable table
# for each skymodel. We do the calculation in chunks of nworkers skymodels.
all_skymodel_blockvis = copy_visibility(block_vis, zero=True)
all_skymodel_vis = convert_blockvisibility_to_visibility(
all_skymodel_blockvis)
ngroup = 8
future_vis = arlexecute.scatter(all_skymodel_vis)
chunks = [
all_skymodel[i:i + ngroup] for i in range(0, len(all_skymodel), ngroup)
]
for chunk in chunks:
result = predict_skymodel_list_arlexecute_workflow(future_vis,
chunk,
context='2d',
docal=True)
work_vis = arlexecute.compute(result, sync=True)
for w in work_vis:
all_skymodel_vis.data['vis'] += w.data['vis']
assert numpy.max(numpy.abs(all_skymodel_vis.data['vis'])) > 0.0
all_skymodel_blockvis = convert_visibility_to_blockvisibility(
all_skymodel_vis)
def actualSetup(self, nsources=None, nvoronoi=None):
n_workers = 8
# Set up the observation: 10 minutes at transit, with 10s integration.
# Skip 5/6 points to avoid outstation redundancy
nfreqwin = 1
ntimes = 3
self.rmax = 2500.0
dec = -40.0 * u.deg
frequency = [1e8]
channel_bandwidth = [0.1e8]
times = numpy.linspace(-10.0, 10.0,
ntimes) * numpy.pi / (3600.0 * 12.0)
phasecentre = SkyCoord(ra=+0.0 * u.deg,
dec=dec,
frame='icrs',
equinox='J2000')
low = create_named_configuration('LOWBD2', rmax=self.rmax)
centre = numpy.mean(low.xyz, axis=0)
distance = numpy.hypot(low.xyz[:, 0] - centre[0],
low.xyz[:, 1] - centre[1],
low.xyz[:, 2] - centre[2])
lowouter = low.data[distance > 1000.0][::6]
lowcore = low.data[distance < 1000.0][::3]
low.data = numpy.hstack((lowcore, lowouter))
blockvis = create_blockvisibility(
low,
times,
frequency=frequency,
channel_bandwidth=channel_bandwidth,
weight=1.0,
phasecentre=phasecentre,
polarisation_frame=PolarisationFrame("stokesI"),
zerow=True)
vis = convert_blockvisibility_to_visibility(blockvis)
advice = advise_wide_field(vis, guard_band_image=2.0, delA=0.02)
cellsize = advice['cellsize']
npixel = advice['npixels2']
small_model = create_image_from_visibility(blockvis,
npixel=512,
frequency=frequency,
nchan=nfreqwin,
cellsize=cellsize,
phasecentre=phasecentre)
vis.data['imaging_weight'][...] = vis.data['weight'][...]
vis = weight_list_serial_workflow([vis], [small_model])[0]
vis = taper_list_serial_workflow([vis], 3 * cellsize)[0]
blockvis = convert_visibility_to_blockvisibility(vis)
# ### Generate the model from the GLEAM catalog, including application of the primary beam.
beam = create_image_from_visibility(blockvis,
npixel=npixel,
frequency=frequency,
nchan=nfreqwin,
cellsize=cellsize,
phasecentre=phasecentre)
beam = create_low_test_beam(beam)
flux_limit = 0.5
original_gleam_components = create_low_test_skycomponents_from_gleam(
flux_limit=flux_limit,
phasecentre=phasecentre,
frequency=frequency,
polarisation_frame=PolarisationFrame('stokesI'),
radius=0.15)
all_components = apply_beam_to_skycomponent(original_gleam_components,
beam)
all_components = filter_skycomponents_by_flux(all_components,
flux_min=flux_limit)
voronoi_components = filter_skycomponents_by_flux(all_components,
flux_min=1.5)
def max_flux(elem):
return numpy.max(elem.flux)
voronoi_components = sorted(voronoi_components,
key=max_flux,
reverse=True)
if nsources is not None:
all_components = [all_components[0]]
if nvoronoi is not None:
voronoi_components = [voronoi_components[0]]
self.screen = import_image_from_fits(
arl_path('data/models/test_mpc_screen.fits'))
all_gaintables = create_gaintable_from_screen(blockvis, all_components,
self.screen)
gleam_skymodel_noniso = [
SkyModel(components=[all_components[i]],
gaintable=all_gaintables[i])
for i, sm in enumerate(all_components)
]
# ### Now predict the visibility for each skymodel and apply the gaintable for that skymodel,
# returning a list of visibilities, one for each skymodel. We then sum these to obtain
# the total predicted visibility. All images and skycomponents in the same skymodel
# get the same gaintable applied which means that in this case each skycomponent has a separate gaintable.
self.all_skymodel_noniso_vis = convert_blockvisibility_to_visibility(
blockvis)
ngroup = n_workers
future_vis = arlexecute.scatter(self.all_skymodel_noniso_vis)
chunks = [
gleam_skymodel_noniso[i:i + ngroup]
for i in range(0, len(gleam_skymodel_noniso), ngroup)
]
for chunk in chunks:
result = predict_skymodel_list_arlexecute_workflow(future_vis,
chunk,
context='2d',
docal=True)
work_vis = arlexecute.compute(result, sync=True)
for w in work_vis:
self.all_skymodel_noniso_vis.data['vis'] += w.data['vis']
assert numpy.max(
numpy.abs(self.all_skymodel_noniso_vis.data['vis'])) > 0.0
self.all_skymodel_noniso_blockvis = convert_visibility_to_blockvisibility(
self.all_skymodel_noniso_vis)
# ### Remove weaker of components that are too close (0.02 rad)
idx, voronoi_components = remove_neighbouring_components(
voronoi_components, 0.02)
model = create_image_from_visibility(blockvis,
npixel=npixel,
frequency=frequency,
nchan=nfreqwin,
cellsize=cellsize,
phasecentre=phasecentre)
# Use the gaintable for the brightest component as the starting gaintable
all_gaintables[0].gain[...] = numpy.conjugate(
all_gaintables[0].gain[...])
all_gaintables[0].gain[...] = 1.0 + 0.0j
self.theta_list = initialize_skymodel_voronoi(model,
voronoi_components,
all_gaintables[0])
