def get_next_memory_windows(trace_file, cache_type, cache_size, n_early_stop,
seq_start, parameters, args_global):
# use 80% warmup, manually check for unimodal behavior
n_warmup = int(0.8 * n_early_stop)
# per cache size parameters overwrite other parameters
df = database.load_reports(
trace_file=trace_file,
cache_type=cache_type,
cache_size=str(cache_size),
seq_start=str(seq_start),
n_early_stop=str(n_early_stop),
n_warmup=n_warmup,
version=parameters['version'], # use version as a strong key
dburi=parameters["dburi"],
dbcollection=parameters["dbcollection"],
)
if len(df) == 0:
next_windows = np.linspace(1,
int(0.4 * n_early_stop),
args_global['n_beam'] + 1,
dtype=int)[1:]
else:
# window at most 40% of length
parameter_space = ParameterSpace(
[ContinuousParameter('x', 1, int(0.4 * n_early_stop))])
bo = GPBayesianOptimization(
variables_list=parameter_space.parameters,
X=df['memory_window'].values.reshape(-1, 1),
Y=df['byte_miss_ratio'].values.reshape(-1, 1),
batch_size=args_global['n_beam'])
next_windows = bo.suggest_new_locations().reshape(-1).astype(int)
return next_windows
def get_tasks_per_cache_size(trace_file, cache_type, cache_size, parameters,
args_global):
n_req = parameters['n_req']
n_validation = int(n_req * args_global['ratio_validation'])
n_warmup = int(0.8 * n_validation)
# TODO: ideally need to match all parameters. So this means doesn't support multiple values for same lrb
# parameter
df = database.load_reports(
trace_file=trace_file,
cache_type=cache_type,
# no cache size because may check smaller cache sizes
n_early_stop=str(n_validation),
n_warmup=n_warmup,
lrb_version=parameters['lrb_version'], # use version as a strong key
dburi=parameters["dburi"],
dbcollection=parameters["dbcollection"],
)
tasks = get_validation_tasks_per_cache_size(trace_file, cache_type,
cache_size, parameters,
args_global, df)
if len(tasks) != 0:
return tasks
need_fitting = check_need_fitting(cache_size, parameters, args_global, df)
if need_fitting == False:
return get_evaluation_task(trace_file, cache_type, cache_size,
parameters, args_global, df)
return get_fitting_task(trace_file, cache_type, cache_size, parameters,
args_global, df)
def _get_evaluation_task(trace_file, cache_type, cache_size, memory_window, parameters):
n_early_stop = parameters['n_early_stop']
# TODO: ideally need to match all parameters. So this means doesn't support multiple values for same lrb
# parameter
df = database.load_reports(
trace_file=trace_file,
cache_type=cache_type,
cache_size=str(cache_size),
n_early_stop=str(n_early_stop),
n_warmup=0,
memory_window=str(memory_window),
version=parameters['version'], # use version as a strong key
dburi=parameters["dburi"],
dbcollection=parameters["dbcollection"],
)
if len(df) != 0:
# test this before
return []
else:
task = _get_task(trace_file, cache_type, cache_size, parameters, n_early_stop, memory_window)
return [task]