def run (self):
""" run the application graph
"""
# cannot run unless weights file exists
if self._weights_file is None:
print "run aborted: weights file not given"
return
# may need to reload initial weights file if
# application graph was modified after load
if not self._weights_loaded:
if not self.read_Lens_weights_file (self._weights_file):
print "run aborted: error reading weights file"
# cannot run unless example set exists
if self._ex_set is None:
print "run aborted: no example set"
return
# cannot run unless examples have been loaded
if not self._ex_set.examples_loaded:
print "run aborted: examples not loaded"
return
# generate summary set, example and event data
self._num_examples = self._ex_set.compile (self)
if self._num_examples == 0:
print "run aborted: error compiling example set"
return
# generate machine graph
self.generate_machine_graph ()
# run application based on the machine graph
g.run (None)
# wait for the application to finish
print "running: waiting for application to finish"
_txrx = g.transceiver ()
_app_id = globals_variables.get_simulator ()._app_id
#lap _running = _txrx.get_core_state_count (_app_id, CPUState.RUNNING)
_finished = _txrx.get_core_state_count (_app_id, CPUState.FINISHED)
while _finished < self._num_vertices:
time.sleep (0.5)
_error = _txrx.get_core_state_count\
(_app_id, CPUState.RUN_TIME_EXCEPTION)
_wdog = _txrx.get_core_state_count (_app_id, CPUState.WATCHDOG)
if _error > 0 or _wdog > 0:
print "application stopped: cores failed ({}\
RTE, {} WDOG)".format (_error, _wdog)
break
#lap _running = _txrx.get_core_state_count (_app_id, CPUState.RUNNING)
_finished = _txrx.get_core_state_count (_app_id, CPUState.FINISHED)
def run(self, mbs, number_of_repeats):
# setup system
sim.setup(model_binary_module=(
test_extra_monitor_core_data_extraction_multiple_locations),
n_chips_required=49 * 2)
# build vertices
locs = [(0, 0), (2, 2), (7, 7), (3, 0), (1, 0), (0, 1), (3, 3), (4, 4),
(5, 5), (3, 5), (4, 0), (7, 4), (8, 4), (4, 8), (11, 11),
(11, 0), (0, 11), (6, 3), (0, 6)]
writers = list()
for chip_x, chip_y in locs:
writer = SDRAMWriter(mbs,
constraint=ChipAndCoreConstraint(
chip_x, chip_y))
# add vertices to graph
sim.add_machine_vertex_instance(writer)
writers.append(writer)
sim.run(12)
# get placements for extraction
placements = sim.placements()
machine = sim.machine()
extra_monitor_vertices = sim.globals_variables. \
get_simulator()._last_run_outputs[
'MemoryExtraMonitorVertices']
extra_monitor_gatherers = sim.globals_variables. \
get_simulator()._last_run_outputs[
'MemoryMCGatherVertexToEthernetConnectedChipMapping']
time_out_setter = extra_monitor_gatherers[(0, 0)]
time_out_setter.set_cores_for_data_extraction(sim.transceiver(),
extra_monitor_vertices,
placements)
for _ in range(0, number_of_repeats):
for writer in writers:
writer_placement = placements.get_placement_of_vertex(writer)
writer_chip = \
machine.get_chip_at(writer_placement.x, writer_placement.y)
writer_nearest_ethernet = machine.get_chip_at(
writer_chip.nearest_ethernet_x,
writer_chip.nearest_ethernet_y)
receiver = None
gatherer = extra_monitor_gatherers[(writer_nearest_ethernet.x,
writer_nearest_ethernet.y)]
for vertex in extra_monitor_vertices:
placement = placements.get_placement_of_vertex(vertex)
if (placement.x == writer_placement.x
and placement.y == writer_placement.y):
receiver = vertex
start = float(time.time())
data = gatherer.get_data(
sim.transceiver(),
placements.get_placement_of_vertex(receiver),
self._get_data_region_address(sim.transceiver(),
writer_placement),
writer.mbs_in_bytes)
end = float(time.time())
print("time taken to extract {} MB is {}. MBS of {}".format(
mbs, end - start, (mbs * 8) / (end - start)))
self._check_data(data)
time_out_setter.unset_cores_for_data_extraction(
sim.transceiver(), extra_monitor_vertices, placements)
# add verts to graph
sim.add_machine_vertex_instance(receiver)
# run forever (to allow better speed testing)
sim.run()
# get placements for extraction
placements = sim.placements()
# try getting data via mc transmission
start = None
end = None
data = None
sim.transceiver().set_watch_dog(False)
try:
print("starting data gathering")
start = float(time.time())
data = receiver.get_data(
sim.transceiver(),
placements.get_placement_of_vertex(receiver))
end = float(time.time())
# end sim
sim.stop()
# print data
seconds = float(end - start)
speed = (mbs * 8) / seconds
print("Read {} MB in {} seconds ({} Mb/s)".format(mbs, seconds, speed))
def transceiver():
return front_end.transceiver()
# build and add edge to graph
sim.add_machine_edge_instance(MachineEdge(reader, receiver), "TRANSMIT")
# run forever (to allow better speed testing)
sim.run()
# get placements for extraction
placements = sim.placements()
# try getting data via mc transmission
start = None
end = None
data = None
sim.transceiver().set_watch_dog(False)
try:
print("starting data gathering")
start = float(time.time())
data = receiver.get_data(sim.transceiver(),
placements.get_placement_of_vertex(reader))
end = float(time.time())
# end sim
sim.stop()
# check data is correct here
ints = struct.unpack("<{}I".format(len(data) // 4), data)
start_value = 0
for value in ints:
if value != start_value:
placements = sim.placements()
# try getting data via mc transmission
start = None
end = None
data = None
# set time outs using new interface (
# clunky, but will be hidden in interface at later date)
extra_monitor_vertices = sim.globals_variables. \
get_simulator()._last_run_outputs['MemoryExtraMonitorVertices']
try:
print("starting data gathering")
start = float(time.time())
data = receiver.get_data(sim.transceiver(),
placements.get_placement_of_vertex(reader),
extra_monitor_vertices, placements)
end = float(time.time())
# end sim
sim.stop()
# print data
seconds = float(end - start)
speed = (mbs * 8) / seconds
print("Read {} MB in {} seconds ({} Mb/s)".format(mbs, seconds, speed))
# check data is correct here
ints = struct.unpack("<{}I".format(len(data) // 4), data)
start_value = 0
for value in ints:
def run_mcmc(model,
data,
n_samples,
burn_in=2000,
thinning=5,
degrees_of_freedom=3.0,
seed=None,
n_chips=None,
n_boards=None):
""" Executes an MCMC model, returning the received samples
:param model: The MCMCModel to be used
:param data: The data to sample
:param n_samples: The number of samples to generate
:param burn_in:\
no of MCMC transitions to reach apparent equilibrium before\
generating inference samples
:param thinning:\
sampling rate i.e. 5 = 1 sample for 5 generated steps
:param degrees_of_freedom:\
The number of degrees of freedom to jump around with
:param seed: The random seed to use
:param n_chips: The number of chips to run the model on
:param root_finder: Use the root finder by adding root finder vertices
:param cholesky: Use the Cholesky algorithm by adding Cholesky vertices
:return: The samples read
:rtype: A numpy array with fields for each model state variable
"""
# Set up the simulation
g.setup(n_boards_required=n_boards,
n_chips_required=n_chips,
model_binary_module=model_binaries)
# Get the number of cores available for use
n_cores = 0
machine = g.machine()
# Create a coordinator for each board
coordinators = dict()
boards = dict()
for chip in machine.ethernet_connected_chips:
# Create a coordinator
coordinator = MCMCCoordinatorVertex(model, data, n_samples, burn_in,
thinning, degrees_of_freedom, seed)
g.add_machine_vertex_instance(coordinator)
# Put the coordinator on the Ethernet chip
coordinator.add_constraint(ChipAndCoreConstraint(chip.x, chip.y))
coordinators[chip.x, chip.y] = coordinator
boards[chip.x, chip.y] = chip.ip_address
# Go through all the chips and add the workhorses
n_chips_on_machine = machine.n_chips
n_workers = 0
if (model.root_finder):
n_root_finders = 0
if (model.cholesky):
n_cholesky = 0
for chip in machine.chips:
# Count the cores in the processor
# (-1 if this chip also has a coordinator)
n_cores = len([p for p in chip.processors if not p.is_monitor])
if (chip.x, chip.y) in coordinators:
n_cores -= 3 # coordinator and extra_monitor_support (2)
if (model.root_finder):
if (model.cholesky):
n_cores = n_cores // 3
else:
n_cores = n_cores // 2
else:
n_cores -= 1 # just extra_monitor_support
if (model.root_finder):
if (model.cholesky):
n_cores = n_cores // 3
else:
n_cores = n_cores // 2
# Find the coordinator for the board (or 0, 0 if it is missing)
eth_x = chip.nearest_ethernet_x
eth_y = chip.nearest_ethernet_y
coordinator = coordinators.get((eth_x, eth_y))
if coordinator is None:
print("Warning - couldn't find {}, {} for chip {}, {}".format(
eth_x, eth_y, chip.x, chip.y))
coordinator = coordinators[0, 0]
print("Using coordinator ", coordinator)
# hard-code remove some cores (chip power monitor etc.) just
# to see what happens
# n_cores -= non_worker_cores_per_chip
# print 'n_cores: ', n_cores
# Add a vertex for each core
for _ in range(n_cores):
# Create the vertex and add it to the graph
vertex = MCMCVertex(coordinator, model)
n_workers += 1
g.add_machine_vertex_instance(vertex)
# Put the vertex on the same board as the coordinator
vertex.add_constraint(ChipAndCoreConstraint(chip.x, chip.y))
# Add an edge from the coordinator to the vertex, to send the data
g.add_machine_edge_instance(MachineEdge(coordinator, vertex),
coordinator.data_partition_name)
# Add an edge from the vertex to the coordinator,
# to send acknowledgement
g.add_machine_edge_instance(MachineEdge(vertex, coordinator),
coordinator.acknowledge_partition_name)
if (model.root_finder):
# Create a root finder vertex
rf_vertex = MCMCRootFinderVertex(vertex, model)
n_root_finders += 1
g.add_machine_vertex_instance(rf_vertex)
# put it on the same chip as the standard mcmc vertex?
# no - put it on a "nearby" chip, however that works
rf_vertex.add_constraint(ChipAndCoreConstraint(chip.x, chip.y))
# Add an edge from mcmc vertex to root finder vertex,
# to "send" the data - need to work this out
g.add_machine_edge_instance(MachineEdge(vertex, rf_vertex),
vertex.parameter_partition_name)
# Add edge from root finder vertex back to mcmc vertex
# to send acknowledgement / result - need to work this out
g.add_machine_edge_instance(MachineEdge(rf_vertex, vertex),
vertex.result_partition_name)
if (model.cholesky):
# Create a Cholesky vertex
cholesky_vertex = MCMCCholeskyVertex(vertex, model)
n_cholesky += 1
g.add_machine_vertex_instance(cholesky_vertex)
# put it on the same chip as the standard mcmc vertex?
# no - put it on a "nearby" chip, however that works
cholesky_vertex.add_constraint(
ChipAndCoreConstraint(chip.x, chip.y))
# Add an edge from mcmc vertex to Cholesky vertex,
# to "send" the data - need to work this out
g.add_machine_edge_instance(
MachineEdge(vertex, cholesky_vertex),
vertex.cholesky_partition_name)
# Add edge from Cholesky vertex back to mcmc vertex
# to send acknowledgement / result - need to work this out
g.add_machine_edge_instance(
MachineEdge(cholesky_vertex, vertex),
vertex.cholesky_result_partition_name)
start_computing_time = time.time()
logger.info("n_chips_on_machine {}".format(n_chips_on_machine))
logger.info("Running {} worker cores".format(n_workers))
if (model.root_finder):
logger.info("Running {} root finder cores".format(n_root_finders))
if (model.cholesky):
logger.info("Running {} Cholesky cores".format(n_cholesky))
# Run the simulation
g.run_until_complete()
mid_computing_time = time.time()
# Wait for the application to finish
txrx = g.transceiver()
app_id = globals_variables.get_simulator()._app_id
logger.info("Running {} worker cores".format(n_workers))
if (model.root_finder):
logger.info("Running {} root finder cores".format(n_root_finders))
if (model.cholesky):
logger.info("Running {} Cholesky cores".format(n_cholesky))
logger.info("Waiting for application to finish...")
running = txrx.get_core_state_count(app_id, CPUState.RUNNING)
# there are now cores doing extra_monitor etc.
non_worker_cores = n_chips_on_machine + (2 * len(boards))
while running > non_worker_cores:
time.sleep(0.5)
error = txrx.get_core_state_count(app_id, CPUState.RUN_TIME_EXCEPTION)
watchdog = txrx.get_core_state_count(app_id, CPUState.WATCHDOG)
if error > 0 or watchdog > 0:
error_msg = "Some cores have failed ({} RTE, {} WDOG)".format(
error, watchdog)
raise Exception(error_msg)
running = txrx.get_core_state_count(app_id, CPUState.RUNNING)
print('running: ', running)
finish_computing_time = time.time()
# Get the data back
samples = dict()
for coord, coordinator in iteritems(coordinators):
samples[coord[0],
coord[1]] = coordinator.read_samples(g.buffer_manager())
# Close the machine
g.stop()
finish_time = time.time()
# Note: this timing appears to be incorrect now; needs looking at
print("Overhead time is %s seconds" % (start_computing_time - start_time))
print("Computing time is %s seconds" %
(finish_computing_time - start_computing_time))
print("run_until_complete takes %s seconds" %
(mid_computing_time - start_computing_time))
print("Data collecting time is %s seconds" %
(finish_time - finish_computing_time))
print("Overall running time is %s seconds" % (finish_time - start_time))
return samples
def run_model(data, n_chips=None, n_ihcan=0, fs=44100, resample_factor=1):
# Set up the simulation
g.setup(n_chips_required=n_chips, model_binary_module=model_binaries)
# Get the number of cores available for use
n_cores = 0
machine = g.machine()
# Create a OME for each chip
boards = dict()
#changed to lists to ensure data is read back in the same order that verticies are instantiated
ihcans = list()
cf_index = 0
count = 0
for chip in machine.chips:
if count >= n_chips:
break
else:
boards[chip.x, chip.y] = chip.ip_address
for j in range(n_ihcan):
ihcan = IHCANVertex(data[j][:], fs, resample_factor)
g.add_machine_vertex_instance(ihcan)
# constrain placement to local chip
ihcan.add_constraint(ChipAndCoreConstraint(chip.x, chip.y))
#ihcans[chip.x, chip.y,j] = ihcan
ihcans.append(ihcan)
count = count + 1
# Run the simulation
g.run(None)
# Wait for the application to finish
txrx = g.transceiver()
app_id = globals_variables.get_simulator()._app_id
#logger.info("Running {} worker cores".format(n_workers))
logger.info("Waiting for application to finish...")
running = txrx.get_core_state_count(app_id, CPUState.RUNNING)
while running > 0:
time.sleep(0.5)
error = txrx.get_core_state_count(app_id, CPUState.RUN_TIME_EXCEPTION)
watchdog = txrx.get_core_state_count(app_id, CPUState.WATCHDOG)
if error > 0 or watchdog > 0:
error_msg = "Some cores have failed ({} RTE, {} WDOG)".format(
error, watchdog)
raise Exception(error_msg)
running = txrx.get_core_state_count(app_id, CPUState.RUNNING)
# Get the data back
samples = list()
progress = ProgressBar(len(ihcans), "Reading results")
for ihcan in ihcans:
samples.append(ihcan.read_samples(g.buffer_manager()))
progress.update()
progress.end()
samples = numpy.hstack(samples)
# Close the machine
g.stop()
print "channels running: ", len(ihcans) / 5.0
print "output data: {} fibres with length {}".format(
len(ihcans) * 2, len(samples))
#if(len(samples) != len(ihcans)*2*numpy.floor(len(data[0][0])/100)*100*(1.0/resample_factor)):
if (len(samples) !=
len(ihcans) * 2 * numpy.floor(len(data[0][0]) / 96) * 96):
#print "samples length {} isn't expected size {}".format(len(samples),len(ihcans)*2*numpy.floor(len(data[0][0])/100)*100*(1.0/resample_factor))
print "samples length {} isn't expected size {}".format(
len(samples),
len(ihcans) * 2 * numpy.floor(len(data[0][0]) / 96) * 96)
return samples
MachineEdge(vertices[x][y],
vertices[dest_x][dest_y],
label=compass), ConwayBasicCell.PARTITION_ID)
# run the simulation
front_end.run(runtime)
# get recorded data
recorded_data = dict()
# get the data per vertex
if not front_end.use_virtual_machine():
for x in range(0, MAX_X_SIZE_OF_FABRIC):
for y in range(0, MAX_Y_SIZE_OF_FABRIC):
recorded_data[x, y] = vertices[x][y].get_data(
front_end.transceiver(),
front_end.placements().get_placement_of_vertex(vertices[x][y]),
front_end.no_machine_time_steps())
# visualise it in text form (bad but no vis this time)
for time in range(0, runtime):
print("at time {}".format(time))
output = ""
for y in range(MAX_X_SIZE_OF_FABRIC - 1, 0, -1):
for x in range(0, MAX_Y_SIZE_OF_FABRIC):
output += "X" if recorded_data[x, y][time] else " "
output += "\n"
print(output)
print("\n\n")
# clear the machine
