def weak_scaling_flow():
"""
Weak scaling analysis.
"""
# Basic parameters
verbose = True
run_pre_analysis = True
# batch_folder = check_relative_path("data/scaling_output")
base_figure_folder = check_relative_path("figures/")
base_figure_folder = os.path.join(base_figure_folder, "weak_scaling")
check_folder(base_figure_folder, verbose=verbose)
default_params = get_default_parameters(data_batch_folder="temp",
include_euclidean_time_obs=False)
# Build correct files list
# weak_scaling_files = filter(
# lambda _f: True if "weak_scaling" in _f else False,
# os.listdir(batch_folder))
with open(datapath, "r") as f:
string_scaling_times = json.load(f)["runs"]
string_scaling_times = filter(
lambda _f: True
if "weak_scaling" in _f["runname"] else False, string_scaling_times)
# Splits into gen, io, flow
weakrong_scaling = filter(
lambda _f: True
if "gen" in _f["runname"] else False, string_scaling_times)
weakong_scaling = filter(
lambda _f: True
if "io" in _f["runname"] else False, string_scaling_times)
weaktrong_scaling = filter(
lambda _f: True
if "flow" in _f["runname"] else False, string_scaling_times)
def distribution_analysis():
"""Analysis for different SU3 epsilon matrix geeration values."""
default_params = get_default_parameters(data_batch_folder="temp")
verbose = True
use_pickle = False
pickle_name = "distribution_analysis_data_pickle.pkl"
########## Distribution analysis ##########
dist_eps = [0.05, 0.10, 0.20, 0.24, 0.30, 0.40, 0.60]
def create_dist_batch_set(default_parameters, eps):
def clean_str(s):
return str("%-2.2f" % s).replace(".", "")
dist_data_beta60_analysis = copy.deepcopy(default_parameters)
# Ensuring that the distribution runs folder exist
dist_data_beta60_analysis["batch_folder"] = (
"../data/distribution_tests/distribution_runs")
if not os.path.isdir(dist_data_beta60_analysis["batch_folder"]):
dist_data_beta60_analysis["batch_folder"] = \
os.path.join("..", dist_data_beta60_analysis["batch_folder"])
dist_data_beta60_analysis["batch_name"] = \
"distribution_test_eps{0:s}".format(clean_str(eps))
dist_data_beta60_analysis["beta"] = 6.0
dist_data_beta60_analysis["num_bins_per_int"] = 16
dist_data_beta60_analysis["bin_range"] = [-2.1, 2.1]
dist_data_beta60_analysis["hist_flow_times"] = [0, 250, 600]
dist_data_beta60_analysis["NCfgs"] = get_num_observables(
dist_data_beta60_analysis["batch_folder"],
dist_data_beta60_analysis["batch_name"])
dist_data_beta60_analysis["obs_file"] = "6_6.00" # 6^3x12, beta=6.0
dist_data_beta60_analysis["N"] = 6
dist_data_beta60_analysis["NT"] = 12
dist_data_beta60_analysis["color"] = "#377eb8"
return dist_data_beta60_analysis
dist_param_list = [
create_dist_batch_set(default_params, _eps) for _eps in dist_eps
]
# dist_param_list = dist_param_list[:2]
# exit("not performing the regular pre-analysis.")
# Submitting distribution analysis
for analysis_parameters in dist_param_list:
pre_analysis.pre_analysis(analysis_parameters)
# Use post_analysis data for further analysis.
data = {}
for eps, param in zip(dist_eps, dist_param_list):
print "Loading data for eps={0:.2f}".format(eps)
data[eps] = post_analysis.PostAnalysisDataReader(
[param], observables_to_load=param["observables"])
# Plot topc
distribution_plotter(data,
"topc",
r"$\sqrt{8t_f}$",
r"$\langle Q \rangle$",
verbose=verbose)
# Plot topsus
distribution_plotter(data,
"topsus",
r"$\sqrt{8t_f}$",
r"$\chi(\langle Q^2 \rangle)$",
verbose=verbose)
# Plot plaq
distribution_plotter(data,
"plaq",
r"$\sqrt{8t_f}$",
r"$\langle P \rangle$",
verbose=verbose)
def beta645_L32_analysis():
from pre_analysis.pre_analyser import pre_analysis
from post_analysis.post_analyser import post_analysis
from default_analysis_params import get_default_parameters
from tools.folderreadingtools import get_num_observables
import copy
import os
# TODO: load b645 32^4 data
# TODO: pre-analyse b645 32^4 data
# TODO: compare b645 32^4 and b645 48^3*96 data in post analysis
#### Different batches
data_batch_folder = "../GluonAction/data9"
data_batch_folder = "../GluonAction/data10"
default_params = get_default_parameters(
data_batch_folder=data_batch_folder)
# obs_exlusions = ["plaq", "energy", "topc", "topc2", "topc4", "topcr", "topcMC", "topsus"]
# obs_exlusions = ["energy", "topsus", "topsust", "topsuste", "topsusMC", "topsusqtq0"]
# observables = observables_euclidean_time
# observables = ["topsus", "topsust", "topsuste", "topsusMC", "topsusqtq0"]
# observables = ["topsusMC"]
# observables = ["topcr", "qtq0eff"]
# observables = ["topcte"]
# observables = observables_euclidean_time
# observables = ["topcr", "topsus"]
# observables = ["topsust", "topsuste", "topsusqtq0"]
# observables = ["topcrMC"]
# observables = ["qtq0eff", "qtq0e"] + ["topsus", "topsust", "topsuste", "topsusMC", "topsusqtq0"]
# observables = ["qtq0eff", "qtq0e"] + ["topsust", "topsuste", "topsusMC", "topsusqtq0"]
# observables = ["topsus", "topsust", "topsuste", "topsusMC", "topsusqtq0"]
# observables = ["topcr"]
# exit("CHECK TOPCR!! @ 34 in main_analysis.py")
# observables = ["topsuste"]
# observables = ["qtq0effMC"]
# observables = ["energy"]
# observables = ["w_t_energy"]
# observables = ["plaq", "energy", "topc", "topct"]
# observables += ["energy"]
# default_params["observables"] = observables
#### Post analysis parameters
line_fit_interval_points = 20
# topsus_fit_targets = [0.3,0.4,0.5,0.58]
# topsus_fit_targets = [0.3, 0.4, 0.5, 0.6] # tf = sqrt(8*t0)
topsus_fit_targets = [0.6]
energy_fit_target = 0.3
#### Different batches
# data_batch_folder = "../GluonAction/data8"
data_batch_folder = "../GluonAction/data10"
# data_batch_folder = "../GluonAction/DataGiovanni"
# data_batch_folder = "../data/topc_modes_8x16"
# Method of continuum extrapolation.
# Options: plateau, plateau_mean, nearest, interpolate, bootstrap
extrapolation_methods = [
"plateau", "plateau_mean", "nearest", "interpolate", "bootstrap"
]
extrapolation_methods = ["plateau"]
extrapolation_methods = ["bootstrap"]
plot_continuum_fit = False
# Topcr reference value. Options: [float], t0beta, article, t0
topcr_t0 = "t0beta"
# Number of different sectors we will analyse in euclidean time
default_params["numsplits_eucl"] = 4
intervals_eucl = [None, None, None, None]
# Number of different sectors we will analyse in monte carlo time
default_params["MC_time_splits"] = 4
# MC_intervals = [[0, 1000], [500, 1000], [500, 1000], [175, 250]]
MC_intervals = [None, None, None, None]
# Extraction point in flow time a*t_f for q0 in qtq0
q0_flow_times = [0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6] # [fermi]
# Flow time indexes in percent to plot qtq0 in euclidean time at
euclidean_time_percents = [0, 0.25, 0.50, 0.75, 1.00]
# euclidean_time_percents = [0]
# Data types to be looked at in the post-analysis.
post_analysis_data_type = ["bootstrap", "jackknife", "unanalyzed"]
post_analysis_data_type = ["bootstrap"]
########## Main analysis ##########
databeta60 = copy.deepcopy(default_params)
databeta60["batch_name"] = "beta60"
databeta60["beta"] = 6.0
databeta60["topc_y_limits"] = [-9, 9]
databeta60["topc2_y_limits"] = [-81, 81]
databeta60["NCfgs"] = get_num_observables(databeta60["batch_folder"],
databeta60["batch_name"])
databeta60["obs_file"] = "24_6.00"
databeta60["MCInt"] = MC_intervals[0]
databeta60["N"] = 24
databeta60["NT"] = 2 * databeta60["N"]
databeta60["color"] = "#e41a1c"
databeta61 = copy.deepcopy(default_params)
databeta61["batch_name"] = "beta61"
databeta61["beta"] = 6.1
databeta61["topc_y_limits"] = [-12, 12]
databeta61["topc2_y_limits"] = [-144, 144]
databeta61["NCfgs"] = get_num_observables(databeta61["batch_folder"],
databeta61["batch_name"])
databeta61["obs_file"] = "28_6.10"
databeta61["MCInt"] = MC_intervals[1]
databeta61["N"] = 28
databeta61["NT"] = 2 * databeta61["N"]
databeta61["color"] = "#377eb8"
databeta62 = copy.deepcopy(default_params)
databeta62["batch_name"] = "beta62"
databeta62["beta"] = 6.2
databeta62["topc_y_limits"] = [-12, 12]
databeta62["topc2_y_limits"] = [-196, 196]
databeta62["NCfgs"] = get_num_observables(databeta62["batch_folder"],
databeta62["batch_name"])
databeta62["obs_file"] = "32_6.20"
databeta62["MCInt"] = MC_intervals[2]
databeta62["N"] = 32
databeta62["NT"] = 2 * databeta62["N"]
databeta62["color"] = "#4daf4a"
databeta645 = copy.deepcopy(default_params)
databeta645["flow_epsilon"] = 0.02
databeta645["batch_name"] = "beta645"
databeta645["beta"] = 6.45
databeta645["topc_y_limits"] = [-15, 15]
databeta645["topc2_y_limits"] = [-300, 300]
databeta645["NCfgs"] = get_num_observables(databeta645["batch_folder"],
databeta645["batch_name"])
databeta645["obs_file"] = "48_6.45"
databeta645["MCInt"] = MC_intervals[3]
databeta645["N"] = 48
databeta645["NT"] = 2 * databeta645["N"]
databeta645["color"] = "#984ea3"
# Adding relevant batches to args
analysis_parameter_list = [databeta60, databeta61, databeta62, databeta645]
# analysis_parameter_list = [databeta60, databeta61, databeta62]
# analysis_parameter_list = [databeta61, databeta62]
# analysis_parameter_list = [databeta62]
# analysis_parameter_list = [databeta645]
section_seperator = "=" * 160
print section_seperator
print "Observables to be analysed: %s" % ", ".join(
default_params["observables"])
print section_seperator + "\n"
#### Submitting main analysis
for analysis_parameters in analysis_parameter_list:
pre_analysis(analysis_parameters)
if not analysis_parameter_list[0]["MCInt"] is None:
assert sum([len(plist["MCInt"]) - len(analysis_parameter_list[0]["MCInt"])
for plist in analysis_parameter_list]) == 0, \
"unequal amount of MC intervals"
#### Submitting post-analysis data
if len(analysis_parameter_list) >= 3:
post_analysis(analysis_parameter_list,
default_params["observables"],
topsus_fit_targets,
line_fit_interval_points,
energy_fit_target,
q0_flow_times,
euclidean_time_percents,
extrapolation_methods=extrapolation_methods,
plot_continuum_fit=plot_continuum_fit,
post_analysis_data_type=post_analysis_data_type,
figures_folder=default_params["figures_folder"],
gif_params=default_params["gif"],
verbose=default_params["verbose"])
else:
msg = "Need at least 3 different beta values to run post analysis"
msg += "(%d given)." % len(analysis_parameter_list)
print msg
def topc_modes_analysis():
"""Analysis for different lattice sizes and their topological charges."""
default_params = get_default_parameters(data_batch_folder="temp")
run_pre_analysis = False
verbose = True
data_path = "../data/"
if not os.path.isdir(data_path):
data_path = "../" + data_path
########## Smaug data 8x16 analysis ##########
smaug8x16_data_beta60_analysis = copy.deepcopy(default_params)
smaug8x16_data_beta60_analysis["batch_folder"] = data_path
smaug8x16_data_beta60_analysis["batch_name"] = "beta60_8x16_run"
smaug8x16_data_beta60_analysis["beta"] = 6.0
smaug8x16_data_beta60_analysis["topc_y_limits"] = [-2, 2]
smaug8x16_data_beta60_analysis["num_bins_per_int"] = 32
smaug8x16_data_beta60_analysis["bin_range"] = [-2.5, 2.5]
smaug8x16_data_beta60_analysis["hist_flow_times"] = [0, 250, 600]
smaug8x16_data_beta60_analysis["NCfgs"] = get_num_observables(
smaug8x16_data_beta60_analysis["batch_folder"],
smaug8x16_data_beta60_analysis["batch_name"])
smaug8x16_data_beta60_analysis["obs_file"] = "8_6.00"
smaug8x16_data_beta60_analysis["N"] = 8
smaug8x16_data_beta60_analysis["NT"] = 16
smaug8x16_data_beta60_analysis["color"] = "#377eb8"
########## Smaug data 12x24 analysis ##########
smaug12x24_data_beta60_analysis = copy.deepcopy(default_params)
smaug12x24_data_beta60_analysis["batch_folder"] = data_path
smaug12x24_data_beta60_analysis["batch_name"] = "beta60_12x24_run"
smaug12x24_data_beta60_analysis["beta"] = 6.0
smaug12x24_data_beta60_analysis["topc_y_limits"] = [-4, 4]
smaug12x24_data_beta60_analysis["num_bins_per_int"] = 16
smaug12x24_data_beta60_analysis["bin_range"] = [-4.5, 4.5]
smaug12x24_data_beta60_analysis["hist_flow_times"] = [0, 250, 600]
smaug12x24_data_beta60_analysis["NCfgs"] = get_num_observables(
smaug12x24_data_beta60_analysis["batch_folder"],
smaug12x24_data_beta60_analysis["batch_name"])
smaug12x24_data_beta60_analysis["obs_file"] = "12_6.00"
smaug12x24_data_beta60_analysis["N"] = 12
smaug12x24_data_beta60_analysis["NT"] = 24
smaug12x24_data_beta60_analysis["color"] = "#377eb8"
########## Smaug data 16x32 analysis ##########
smaug16x32_data_beta61_analysis = copy.deepcopy(default_params)
smaug16x32_data_beta61_analysis["batch_folder"] = data_path
smaug16x32_data_beta61_analysis["batch_name"] = "beta61_16x32_run"
smaug16x32_data_beta61_analysis["beta"] = 6.1
smaug16x32_data_beta61_analysis["topc_y_limits"] = [-8, 8]
smaug16x32_data_beta61_analysis["num_bins_per_int"] = 16
smaug16x32_data_beta61_analysis["bin_range"] = [-7.5, 7.5]
smaug16x32_data_beta61_analysis["hist_flow_times"] = [0, 250, 600]
smaug16x32_data_beta61_analysis["NCfgs"] = get_num_observables(
smaug16x32_data_beta61_analysis["batch_folder"],
smaug16x32_data_beta61_analysis["batch_name"])
smaug16x32_data_beta61_analysis["obs_file"] = "16_6.10"
smaug16x32_data_beta61_analysis["N"] = 16
smaug16x32_data_beta61_analysis["NT"] = 32
smaug16x32_data_beta61_analysis["color"] = "#377eb8"
param_list = [
smaug8x16_data_beta60_analysis, smaug12x24_data_beta60_analysis,
smaug16x32_data_beta61_analysis
]
if run_pre_analysis:
# Submitting analysis
for analysis_parameters in param_list:
pre_analysis(analysis_parameters)
# Loads topc data
data = []
# N_val = [24, 24, 28]
for i, param in enumerate(param_list):
print "Loading data for: {}".format(param["batch_name"])
# fpath = os.path.join(param["batch_folder"], param["batch_name"],
# "{0:d}_{1:.2f}.npy".format(N_val[i],
# param["beta"]))
data_, p = get_data_parameters(param)
data.append({
"data": data_("topc")["obs"].T,
"beta": param["beta"],
"N": param["N"]
})
# print data_("topc")["obs"].shape
# Flow time to plots
flow_times = [0, 250, 600]
# Histogram plotting
xlim = 7.5
NBins = np.arange(-xlim, xlim, 0.05)
for t_f in flow_times:
# Adds unanalyzed data
fig, axes = plt.subplots(3, 1, sharey=False, sharex=True)
for i, ax in enumerate(axes):
lab = r"${0:d}^3\times{1:d}$, $\beta={2:.2f}$".format(
data[i]["N"], data[i]["N"] * 2, data[i]["beta"])
weights = np.ones_like(data[i]["data"][t_f])
weights /= len(data[i]["data"][t_f])
ax.hist(data[i]["data"][t_f],
bins=NBins,
label=lab,
weights=weights)
ax.legend(loc="upper right")
ax.grid(True)
ax.set_xlim(-xlim, xlim)
if i == 1:
ax.set_ylabel(r"$Hits$")
elif i == 2:
ax.set_xlabel(r"$Q$")
# Sets up figure
figpath = "figures/topc_modes_analysis"
if not os.path.isdir(figpath):
figpath = "../" + figpath
check_folder(figpath, verbose=verbose)
figpath = os.path.join(figpath, "topc_modes_tf{}.pdf".format(t_f))
fig.savefig(figpath)
print "Figure saved at {0:s}".format(figpath)
plt.close(fig)
def lattice_updates_analysis():
run_pre_analysis = False
verbose = False
N_corr = [200, 400, 600]
N_updates = [10, 20, 30]
param_list = []
beta = 6.0
figure_folder = "../figures/lattice_updates"
output_folder = "../data/lattice_update_data"
############ Sets up the different N_up/N_corr analysises ##########
# Sets up Slurm output files
if not os.path.isdir(output_folder):
output_folder = os.path.join("..", output_folder)
output_file_path = os.path.join(output_folder, "output_files")
# Sets up empty nested dictionary
output_files = {icorr: {iup: {} for iup in N_updates} for icorr in N_corr}
# Retrieves standard parameters
default_params = get_default_parameters(data_batch_folder="temp",
verbose=verbose)
# Loops through different corr lengths and link update sizes
for icorr in N_corr:
for iup in N_updates:
# Loops over files in directory
for of in os.listdir(output_file_path):
_tmp = re.findall(r"NUP([\d]+)_NCORR([\d]+)", of)[0]
_NUp, _NCorr = list(map(int, _tmp))
# If icorr and iup matches files, we add it to the dictionary
# we created earlier.
if icorr == _NCorr and iup == _NUp:
output_files[icorr][iup] = {
"NUp": iup,
"NCorr": icorr,
"output_path": os.path.join(output_file_path, of)
}
break
# Sets up parameter list for analysis
for icorr in N_corr:
for iup in N_updates:
_params = copy.deepcopy(default_params)
_params["batch_folder"] = output_folder
_params["batch_name"] = \
"B60_NUP{0:d}_NCORR{1:d}".format(iup, icorr)
_params["NCfgs"] = get_num_observables(_params["batch_folder"],
_params["batch_name"])
_params["beta"] = beta
_params["color"] = "#377eb8"
_params["N"] = 16
_params["NT"] = _params["N"] * 2
_params["observables"] = ["plaq", "energy", "topc"]
_params.update(output_files[icorr][iup])
_times = read_run_time(_params["output_path"])
_params["total_runtime"] = _times[-1][-1]
_params["update_time"] = _times[0][0]
param_list.append(_params)
if run_pre_analysis:
# Submitting distribution analysis
for analysis_parameters in param_list:
pre_analysis(analysis_parameters)
print("Success: pre analysis done.")
# Use post_analysis data for further analysis.
data = {icorr: {iup: {} for iup in N_updates} for icorr in N_corr}
for i, _params in enumerate(param_list):
print "Loading data for NCorr={0:d} NUp={1:d}".format(
_params["NCorr"], _params["NUp"])
data[_params["NCorr"]][_params["NUp"]] = {
"data":
post_analysis.PostAnalysisDataReader(
[_params],
observables_to_load=_params["observables"],
verbose=verbose),
"params":
_params,
}
print("Success: post analysis data retrieved.")
X_corr, Y_up = np.meshgrid(N_corr, N_updates)
# Sets up time grid
Z_total_runtimes = np.zeros((3, 3))
Z_update_times = np.zeros((3, 3))
X_flow = np.zeros((3, 3, 251))
Z_autocorr = np.zeros((3, 3, 251))
Z_autocorr_error = np.zeros((3, 3, 251))
for i, icorr in enumerate(N_corr):
for j, iup in enumerate(N_updates):
Z_total_runtimes[i, j] = \
data[icorr][iup]["params"]["total_runtime"]
Z_update_times[i, j] = \
data[icorr][iup]["params"]["update_time"]
_tmp = data[icorr][iup]["data"]["topc"][beta]
Z_autocorr[i, j] = \
_tmp["with_autocorr"]["autocorr"]["tau_int"]
Z_autocorr_error[i, j] = \
_tmp["with_autocorr"]["autocorr"]["tau_int_err"]
X_flow[i, j] = _tmp["with_autocorr"]["unanalyzed"]["x"]
X_flow[i, j] *= data[icorr][iup]["data"].flow_epsilon[6.0]
X_flow[i, j] = np.sqrt(8 * X_flow[i, j])
X_flow[i, j] *= data[icorr][iup]["data"].lattice_sizes[6.0][0]
# Plots update and total run-times on grid
heatmap_plotter(N_corr,
N_updates,
Z_total_runtimes,
"topc_total_runtime.pdf",
xlabel=r"$N_\mathrm{corr}$",
ylabel=r"$N_\mathrm{up}$",
cbartitle=r"$t_\mathrm{total}$",
figure_folder=figure_folder)
heatmap_plotter(N_corr,
N_updates,
Z_update_times,
"topc_update_runtime.pdf",
xlabel=r"$N_\mathrm{corr}$",
ylabel=r"$N_\mathrm{up}$",
cbartitle=r"$t_\mathrm{update}$",
figure_folder=figure_folder)
# Plots final autocorrelations on grid
flow_times = [0, 100, 250]
for tf in flow_times:
heatmap_plotter(N_corr,
N_updates,
Z_autocorr[:, :, tf],
"topc_autocorr_tau{0:d}.pdf".format(tf),
xlabel=r"$N_\mathrm{corr}$",
ylabel=r"$N_\mathrm{up}$",
cbartitle=r"$\tau_\mathrm{int}$",
figure_folder=figure_folder)
heatmap_plotter(N_corr,
N_updates,
Z_autocorr_error[:, :, tf],
"topc_autocorr_err_tau{0:d}.pdf".format(tf),
xlabel=r"$N_\mathrm{corr}$",
ylabel=r"$N_\mathrm{up}$",
cbartitle=r"$\tau_\mathrm{int}$",
figure_folder=figure_folder)
# Plots all of the 9 autocorrs in single figure
plot9_figures(X_flow,
X_corr,
Y_up,
Z_autocorr,
Z_autocorr_error,
"topc_autocorr.pdf",
xlabel=r"$\sqrt{8t_{f}}$",
ylabel=r"$\tau_\mathrm{int}$",
figure_folder=figure_folder,
mark_interval=10)
def main_analysis(run_pre_analysis=True,
run_post_analysis=True,
only_generate_data=False,
observables=None,
post_analysis_data_type=["bootstrap"]):
from pre_analysis.pre_analyser import pre_analysis
from post_analysis.post_analyser import post_analysis
from default_analysis_params import get_default_parameters
from tools.folderreadingtools import get_num_observables
import copy
import os
# Different batches
# data_batch_folder = "../GluonAction/data8"
data_batch_folder = "../GluonAction/data11"
# data_batch_folder = "../GluonAction/DataGiovanni"
# data_batch_folder = "../data/topc_modes_8x16"
data_batch_folder = "../data/data11"
obs_exlusions = ["w_t_energy", "energy", "topcMC", "topsusMC", "qtq0effMC"]
default_params = get_default_parameters(
data_batch_folder=data_batch_folder, obs_exlusions=obs_exlusions)
if not isinstance(observables, type(None)):
default_params["observables"] = observables
# Post analysis parameters
line_fit_interval_points = 20
# topsus_fit_targets = [0.3,0.4,0.5,0.58]
# topsus_fit_targets = [0.3, 0.4, 0.5, 0.6] # tf = sqrt(8*t0)
topsus_fit_targets = [0.6, "t0", "w0", "t0cont", "w0cont"]
energy_fit_target = 0.3
# Will try to use pickled reference scale instead
use_pickled_reference_scale = True
# Method of continuum extrapolation.
# Options: plateau, plateau_mean, nearest, interpolate, bootstrap
extrapolation_methods = [
"plateau", "plateau_mean", "nearest", "interpolate", "bootstrap"
]
# extrapolation_methods = ["plateau"]
extrapolation_methods = ["bootstrap"]
plot_continuum_fit = False
# Number of different sectors we will analyse in euclidean time
default_params["numsplits_eucl"] = 4
intervals_eucl = [None, None, None, None]
# Number of different sectors we will analyse in monte carlo time
default_params["MC_time_splits"] = 4
# MC_intervals = [[0, 1000], [500, 1000], [500, 1000], [175, 250]]
# MC_intervals = [[0, 1000], [0, 1000], [0, 2000], [0, 125]]
MC_intervals = [None, None, None, None]
# Extraction point in flow time a*t_f for q0 in qtq0
q0_flow_times = [0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6] # [fermi]
# Flow time indexes in percent to plot qtq0 in euclidean time at
euclidean_time_percents = [0, 0.25, 0.50, 0.75, 1.00]
# euclidean_time_percents = [0]
# Blocking
default_params["blocking_analysis"] = True
# Check to only generate data for post-analysis
default_params["only_generate_data"] = only_generate_data
########## Main analysis ##########
databeta60 = copy.deepcopy(default_params)
databeta60["batch_name"] = "beta60"
databeta60["ensemble_name"] = r"$A$"
databeta60["beta"] = 6.0
databeta60["block_size"] = 10 # None
databeta60["topc_y_limits"] = [-9, 9]
databeta60["topc2_y_limits"] = [-81, 81]
databeta60["NCfgs"] = get_num_observables(databeta60["batch_folder"],
databeta60["batch_name"])
databeta60["obs_file"] = "24_6.00"
databeta60["MCInt"] = MC_intervals[0]
databeta60["N"] = 24
databeta60["NT"] = 2 * databeta60["N"]
databeta60["color"] = "#e41a1c"
databeta61 = copy.deepcopy(default_params)
databeta61["batch_name"] = "beta61"
databeta61["ensemble_name"] = r"$B$"
databeta61["beta"] = 6.1
databeta61["block_size"] = 10 # None
databeta61["topc_y_limits"] = [-12, 12]
databeta61["topc2_y_limits"] = [-144, 144]
databeta61["NCfgs"] = get_num_observables(databeta61["batch_folder"],
databeta61["batch_name"])
databeta61["obs_file"] = "28_6.10"
databeta61["MCInt"] = MC_intervals[1]
databeta61["N"] = 28
databeta61["NT"] = 2 * databeta61["N"]
databeta61["color"] = "#377eb8"
databeta62 = copy.deepcopy(default_params)
databeta62["batch_name"] = "beta62"
databeta62["ensemble_name"] = r"$C$"
databeta62["beta"] = 6.2
databeta62["block_size"] = 10 # None
databeta62["topc_y_limits"] = [-12, 12]
databeta62["topc2_y_limits"] = [-196, 196]
databeta62["NCfgs"] = get_num_observables(databeta62["batch_folder"],
databeta62["batch_name"])
databeta62["obs_file"] = "32_6.20"
databeta62["MCInt"] = MC_intervals[2]
databeta62["N"] = 32
databeta62["NT"] = 2 * databeta62["N"]
databeta62["color"] = "#4daf4a"
databeta645 = copy.deepcopy(default_params)
databeta645["flow_epsilon"] = 0.02
databeta645["batch_name"] = "beta645"
databeta645["ensemble_name"] = r"$D_2$"
databeta645["beta"] = 6.45
databeta645["block_size"] = 25 # None
databeta645["topc_y_limits"] = [-15, 15]
databeta645["topc2_y_limits"] = [-300, 300]
databeta645["NCfgs"] = get_num_observables(databeta645["batch_folder"],
databeta645["batch_name"])
databeta645["obs_file"] = "48_6.45"
databeta645["MCInt"] = MC_intervals[3]
databeta645["N"] = 48
databeta645["NT"] = 2 * databeta645["N"]
databeta645["color"] = "#984ea3"
# Adding relevant batches to args
analysis_parameter_list = [databeta60, databeta61, databeta62, databeta645]
section_seperator = "=" * 160
print section_seperator
print "Observables to be analysed: %s" % ", ".join(
default_params["observables"])
print section_seperator + "\n"
# Submitting main analysis
if run_pre_analysis:
for analysis_parameters in analysis_parameter_list:
pre_analysis(analysis_parameters)
if not analysis_parameter_list[0]["MCInt"] is None:
assert sum(
[len(plist["MCInt"]) - len(analysis_parameter_list[0]["MCInt"])
for plist in analysis_parameter_list]) == 0, \
"unequal amount of MC intervals"
# Submitting post-analysis data
if run_post_analysis:
if len(analysis_parameter_list) >= 3:
post_analysis(analysis_parameter_list,
default_params["observables"],
topsus_fit_targets,
line_fit_interval_points,
energy_fit_target,
q0_flow_times,
euclidean_time_percents,
extrapolation_methods=extrapolation_methods,
plot_continuum_fit=plot_continuum_fit,
post_analysis_data_type=post_analysis_data_type,
figures_folder=default_params["figures_folder"],
gif_params=default_params["gif"],
verbose=default_params["verbose"])
else:
msg = "Need at least 3 different beta values to run post analysis"
msg += "(%d given)." % len(analysis_parameter_list)
print msg
def thermalization_analysis():
"""Runs the thermalization analysis."""
verbose = True
run_pre_analysis = True
mark_every = 50
mc_cutoff = -1 # Skip every 100 points with 2000 therm-steps!!
batch_folder = check_relative_path("data/thermalization_data")
base_figure_folder = check_relative_path("figures/")
base_figure_folder = os.path.join(base_figure_folder,
"thermalization_analysis")
check_folder(base_figure_folder, verbose=verbose)
default_params = get_default_parameters(data_batch_folder="temp",
include_euclidean_time_obs=False)
############ COLD START #############
cold_beta60_params = copy.deepcopy(default_params)
cold_beta60_params["batch_folder"] = batch_folder
cold_beta60_params["batch_name"] = "B60_THERM_COLD"
cold_beta60_params["load_binary_file"] = False
cold_beta60_params["beta"] = 6.0
cold_beta60_params["topc_y_limits"] = [-2, 2]
cold_beta60_params["num_bins_per_int"] = 32
cold_beta60_params["bin_range"] = [-2.5, 2.5]
cold_beta60_params["hist_flow_times"] = [0, 250, 600]
cold_beta60_params["NCfgs"] = get_num_observables(
cold_beta60_params["batch_folder"], cold_beta60_params["batch_name"])
cold_beta60_params["obs_file"] = "8_6.00"
cold_beta60_params["N"] = 8
cold_beta60_params["NT"] = 16
cold_beta60_params["color"] = "#377eb8"
########## HOT RND START ############
hot_rnd_beta60_params = copy.deepcopy(default_params)
hot_rnd_beta60_params["batch_folder"] = batch_folder
hot_rnd_beta60_params["batch_name"] = "B60_THERM_HOT_RND"
########## HOT RST START ############
hot_rst_beta60_params = copy.deepcopy(default_params)
hot_rst_beta60_params["batch_folder"] = batch_folder
hot_rst_beta60_params["batch_name"] = "B60_THERM_HOT_RST"
if run_pre_analysis:
# Submitting distribution analysis
cold_data = load_observable(cold_beta60_params)
hot_rnd_data = load_observable(hot_rnd_beta60_params)
hot_rst_data = load_observable(hot_rst_beta60_params)
# # Loads post analysis data
# cold_data = post_analysis.PostAnalysisDataReader(
# [cold_beta60_params],
# observables_to_load=cold_beta60_params["observables"],
# verbose=verbose)
# hot_rnd_data = post_analysis.PostAnalysisDataReader(
# [hot_rnd_beta60_params],
# observables_to_load=hot_rnd_beta60_params["observables"],
# verbose=verbose)
# hot_rst_data = post_analysis.PostAnalysisDataReader(
# [hot_rst_beta60_params],
# observables_to_load=hot_rst_beta60_params["observables"],
# verbose=verbose)
# TODO: plot termaliations for the 3 different observables
plot_types = ["default", "loglog", "logx", "logy"]
y_labels = [[r"$P$", r"$Q$", r"$E$"],
[
r"$\frac{|P - \langle P \rangle|}{\langle P \rangle}$",
r"$\frac{|Q - \langle Q \rangle|}{\langle Q \rangle}$",
r"$\frac{|E - \langle E \rangle|}{\langle E \rangle}$"
],
[
r"$|P - \langle P \rangle|$", r"$|Q - \langle Q \rangle|$",
r"$|E - \langle E \rangle|$"
]]
# y_labels[i_dr] = [r"$\langle P \rangle$", r"$\langle P \rangle$",
# r"$\langle P \rangle$"]
subplot_rows = [1, 3]
# Limits to be put on plot
x_limits = [[] for i in range(3)]
y_limits = [[], [], []]
data_representations = ["default", "relerr", "abserr"]
obs_list = cold_data["obs"].keys()
x_label = r"$t_\mathrm{MC}$"
for i_dr, dr in enumerate(data_representations):
for pt in plot_types:
for i_obs, obs in enumerate(obs_list):
for plot_rows in subplot_rows:
# Sets up figure folder for observable
figure_folder = os.path.join(base_figure_folder, obs)
check_folder(figure_folder, verbose=verbose)
# Sets up plot type folder
figure_folder = os.path.join(figure_folder, pt)
check_folder(figure_folder, verbose=verbose)
if obs == "energy":
correction_factor = -1.0 / 64
cold_data["obs"][obs] *= correction_factor
hot_rnd_data["obs"][obs] *= correction_factor
hot_rst_data["obs"][obs] *= correction_factor
# Retrieves data and makes modifications
_cold_data = modify_data(cold_data["obs"][obs][:mc_cutoff],
dr)
_hot_rnd_data = modify_data(
hot_rnd_data["obs"][obs][:mc_cutoff], dr)
_hot_rst_data = modify_data(
hot_rst_data["obs"][obs][:mc_cutoff], dr)
# Creates figure name
figure_name = "{0:s}_{1:s}_{2:s}_{3:d}plotrows.pdf".format(
obs, pt, dr, plot_rows)
plot_data_array(
[np.arange(_cold_data.shape[0]) for i in range(3)],
[_cold_data, _hot_rnd_data, _hot_rst_data],
["Cold start", "Hot start", r"Hot start, $RST$"],
x_label,
y_labels[i_dr][i_obs],
figure_name,
figure_folder,
plot_type=pt,
x_limits=x_limits[i_obs],
y_limits=y_limits[i_obs],
mark_every=mark_every,
subplot_rows=plot_rows)
def topc_modes_analysis():
"""Analysis for different lattice sizes and their topological charges."""
default_params = get_default_parameters(data_batch_folder="temp")
default_params["blocking_analysis"] = True
default_params["observables"] = ["plaq", "topc", "topc2", "topc4", "topcr",
"topsus", "topsusqtq0", "qtq0e",
"qtq0eff", "topcMC"]
default_params["observables"] = ["topc2", "topc4", "topcr"]
# Check to only generate data for post-analysis
default_params["only_generate_data"] = False
run_pre_analysis = False
run_post_analysis = False
# run_pre_analysis = True
# run_post_analysis = True
default_params["verbose"] = True
########## Post analysis parameters ##########
line_fit_interval_points = 20
topsus_fit_targets = [0.5, 0.6]
energy_fit_target = 0.3
q0_flow_times = [0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6] # [fermi]
euclidean_time_percents = [0, 0.25, 0.50, 0.75, 1.00]
extrapolation_methods = ["bootstrap"]
plot_continuum_fit = False
post_analysis_data_type = ["bootstrap"]
figures_folder = "figures/topc_modes_analysis"
data_path = "../data/"
if not os.path.isdir(data_path):
data_path = "../" + data_path
########## Smaug data 8x16 analysis ##########
smaug8x16_data_beta60_analysis = copy.deepcopy(default_params)
smaug8x16_data_beta60_analysis["batch_folder"] = data_path
smaug8x16_data_beta60_analysis["batch_name"] = "beta60_8x16_run"
smaug8x16_data_beta60_analysis["ensemble_name"] = r"$E$"
smaug8x16_data_beta60_analysis["beta"] = 6.0
smaug8x16_data_beta60_analysis["block_size"] = 10 # None
smaug8x16_data_beta60_analysis["topc_y_limits"] = [-2, 2]
smaug8x16_data_beta60_analysis["num_bins_per_int"] = 32
smaug8x16_data_beta60_analysis["bin_range"] = [-2.5, 2.5]
smaug8x16_data_beta60_analysis["hist_flow_times"] = [0, 250, 600]
smaug8x16_data_beta60_analysis["NCfgs"] = get_num_observables(
smaug8x16_data_beta60_analysis["batch_folder"],
smaug8x16_data_beta60_analysis["batch_name"])
smaug8x16_data_beta60_analysis["obs_file"] = "8_6.00"
smaug8x16_data_beta60_analysis["N"] = 8
smaug8x16_data_beta60_analysis["NT"] = 16
smaug8x16_data_beta60_analysis["color"] = "#377eb8"
########## Smaug data 12x24 analysis ##########
smaug12x24_data_beta60_analysis = copy.deepcopy(default_params)
smaug12x24_data_beta60_analysis["batch_folder"] = data_path
smaug12x24_data_beta60_analysis["batch_name"] = "beta60_12x24_run"
smaug12x24_data_beta60_analysis["ensemble_name"] = r"$F$"
smaug12x24_data_beta60_analysis["beta"] = 6.0
smaug12x24_data_beta60_analysis["block_size"] = 10 # None
smaug12x24_data_beta60_analysis["topc_y_limits"] = [-4, 4]
smaug12x24_data_beta60_analysis["num_bins_per_int"] = 16
smaug12x24_data_beta60_analysis["bin_range"] = [-4.5, 4.5]
smaug12x24_data_beta60_analysis["hist_flow_times"] = [0, 100, 600]
smaug12x24_data_beta60_analysis["NCfgs"] = get_num_observables(
smaug12x24_data_beta60_analysis["batch_folder"],
smaug12x24_data_beta60_analysis["batch_name"])
smaug12x24_data_beta60_analysis["obs_file"] = "12_6.00"
smaug12x24_data_beta60_analysis["N"] = 12
smaug12x24_data_beta60_analysis["NT"] = 24
smaug12x24_data_beta60_analysis["color"] = "#377eb8"
########## Smaug data 16x32 analysis ##########
smaug16x32_data_beta61_analysis = copy.deepcopy(default_params)
smaug16x32_data_beta61_analysis["batch_folder"] = data_path
smaug16x32_data_beta61_analysis["batch_name"] = "beta61_16x32_run"
smaug16x32_data_beta61_analysis["ensemble_name"] = r"$G$"
smaug16x32_data_beta61_analysis["beta"] = 6.1
smaug16x32_data_beta61_analysis["block_size"] = 10 # None
smaug16x32_data_beta61_analysis["topc_y_limits"] = [-8, 8]
smaug16x32_data_beta61_analysis["num_bins_per_int"] = 16
smaug16x32_data_beta61_analysis["bin_range"] = [-7.5, 7.5]
smaug16x32_data_beta61_analysis["hist_flow_times"] = [0, 100, 400]
smaug16x32_data_beta61_analysis["NCfgs"] = get_num_observables(
smaug16x32_data_beta61_analysis["batch_folder"],
smaug16x32_data_beta61_analysis["batch_name"])
smaug16x32_data_beta61_analysis["obs_file"] = "16_6.10"
smaug16x32_data_beta61_analysis["N"] = 16
smaug16x32_data_beta61_analysis["NT"] = 32
smaug16x32_data_beta61_analysis["color"] = "#377eb8"
param_list = [
smaug8x16_data_beta60_analysis,
smaug12x24_data_beta60_analysis,
smaug16x32_data_beta61_analysis]
if run_pre_analysis:
# Submitting analysis
for analysis_parameters in param_list:
pre_analysis(analysis_parameters)
# Submitting post-analysis data
if run_post_analysis:
if len(param_list) >= 3:
post_analysis(param_list,
default_params["observables"],
topsus_fit_targets, line_fit_interval_points,
energy_fit_target,
q0_flow_times, euclidean_time_percents,
extrapolation_methods=extrapolation_methods,
plot_continuum_fit=plot_continuum_fit,
post_analysis_data_type=post_analysis_data_type,
figures_folder=figures_folder, # "figures/topc_modes_analysis"
verbose=default_params["verbose"])
else:
msg = "Need at least 3 different beta values to run post analysis"
msg += "(%d given)." % len(analysis_parameter_list)
print msg
# Loads topc data
data = []
# N_val = [24, 24, 28]
for i, param in enumerate(param_list):
print "Loading data for: {}".format(param["batch_name"])
data_, p = get_data_parameters(param)
data.append({"data": data_("topc")["obs"].T,
"beta": param["beta"],
"N": param["N"],
"ensemble_name": param["ensemble_name"]})
# Flow time to plots
flow_times = [0, 25, 50, 100, 150, 250, 450, 600]
# Histogram plotting
xlim = 7.5
NBins = np.arange(-xlim, xlim, 0.05)
for t_f in flow_times:
# Adds unanalyzed data
fig, axes = plt.subplots(len(param_list), 1,
sharey=False, sharex=True)
axes = np.atleast_1d(axes)
for i, ax in enumerate(axes):
# lab = r"${0:d}^3\times{1:d}$, $\beta={2:.2f}$".format(
# data[i]["N"], data[i]["N"]*2, data[i]["beta"])
lab = data[i]["ensemble_name"]
weights = np.ones_like(data[i]["data"][t_f])
weights /= len(data[i]["data"][t_f])
ax.hist(data[i]["data"][t_f], bins=NBins,
label=lab, weights=weights)
ax.legend(loc="upper right")
ax.grid(True)
ax.set_xlim(-xlim, xlim)
if i == 1:
ax.set_ylabel(r"Hits(normalized)")
elif i == 2:
ax.set_xlabel(r"$Q$")
# Sets up figure
figpath = figures_folder
if not os.path.isdir(figpath):
figpath = "../" + figpath
check_folder(figpath, verbose=default_params["verbose"])
figpath = os.path.join(figpath, "topc_modes_tf{}.pdf".format(t_f))
fig.savefig(figpath)
print "Figure saved at {0:s}".format(figpath)
plt.close(fig)
def scaling_analysis():
"""
Scaling analysis.
"""
# TODO: complete load slurm output function
# TODO: add line fitting procedure to plot_scaling function
# TODO: double check what I am plotting makes sense(see pdf)
# Basic parameters
verbose = True
run_pre_analysis = True
json_file = "run_times_updated.json"
datapath = os.path.join(("/Users/hansmathiasmamenvege/Programming/LQCD/"
"data/scaling_output/"), json_file)
slurm_output_folder = check_relative_path("../data/scaling_output")
# Extract times from slurm files and put into json file
if not os.path.isfile(datapath):
print "No {} found. Loading slurm data.".format(json_file)
load_slurm_folder(slurm_output_folder)
# Basic figure setup
base_figure_folder = check_relative_path("figures")
base_figure_folder = os.path.join(base_figure_folder, "scaling")
check_folder(base_figure_folder, verbose=verbose)
# Strong scaling folder setup
strong_scaling_figure_folder = os.path.join(base_figure_folder, "strong")
check_folder(strong_scaling_figure_folder, verbose=verbose)
# Weak scaling folder setup
weak_scaling_figure_folder = os.path.join(base_figure_folder, "weak")
check_folder(weak_scaling_figure_folder, verbose=verbose)
default_params = get_default_parameters(data_batch_folder="temp",
include_euclidean_time_obs=False)
# Loads scaling times and splits into weak and strong
with open(datapath, "r") as f:
scaling_times = json.load(f)["runs"]
strong_scaling_times = filter_scalings(scaling_times, "strong_scaling_np")
weak_scaling_times = filter_scalings(scaling_times, "weak_scaling_np")
# Splits strong scaling into gen, io, flow
gen_strong_scaling = filter_scalings(strong_scaling_times, "gen")
io_strong_scaling = filter_scalings(strong_scaling_times, "io")
flow_strong_scaling = filter_scalings(strong_scaling_times, "flow")
# Splits weak scaling into gen, io, flow
gen_weak_scaling = filter_scalings(weak_scaling_times, "gen")
io_weak_scaling = filter_scalings(weak_scaling_times, "io")
flow_weak_scaling = filter_scalings(weak_scaling_times, "flow")
# Adds number of processors to strong scaling
gen_strong_scaling = add_numprocs(gen_strong_scaling)
io_strong_scaling = add_numprocs(io_strong_scaling)
flow_strong_scaling = add_numprocs(flow_strong_scaling)
# Adds number of processors to strong scaling
gen_weak_scaling = add_numprocs(gen_weak_scaling)
io_weak_scaling = add_numprocs(io_weak_scaling)
flow_weak_scaling = add_numprocs(flow_weak_scaling)
scalings = [
gen_strong_scaling, io_strong_scaling, flow_strong_scaling,
gen_weak_scaling, io_weak_scaling, flow_weak_scaling
]
for time_type in ["update_time", "time"]:
# Loops over scaling values in scalings
for sv in scalings:
x = [i["NP"] for i in sv]
y = [i[time_type] for i in sv]
# Sets up filename and folder name
_scaling = list(set([i["runname"].split("_")[0] for i in sv]))
_sc_part = list(set([i["runname"].split("_")[-1] for i in sv]))
assert len(_scaling) == 1, \
"incorrect sv type list: {}".format(_scaling)
assert len(_sc_part) == 1, \
"incorrect sv part list length: {}".format(_sc_part)
_sc_part = _sc_part[0]
_scaling = _scaling[0]
figure_name = "{}_{}_{}.pdf".format(_scaling, _sc_part, time_type)
if _sc_part != "gen" and time_type == "update_time":
print "Skipping {}".format(figure_name)
continue
# Sets correct figure folder
if _scaling == "strong":
figure_folder = strong_scaling_figure_folder
elif _scaling == "weak":
figure_folder = weak_scaling_figure_folder
else:
raise ValueError("Scaling type not recognized for"
" folder: {}".format(_scaling))
plot_scaling(
x, y, _sc_part.capitalize(), r"$N_p$", r"$t_\mathrm{%s}$" %
time_type.replace("_", r"\ ").capitalize(), figure_folder,
figure_name)
def scaling_analysis():
"""
Scaling analysis.
"""
# Basic parameters
verbose = True
run_pre_analysis = True
json_file = "run_times_tmp.json"
datapath = os.path.join(("/Users/hansmathiasmamenvege/Programming/LQCD/"
"data/scaling_output/"), json_file)
datapath = os.path.join(("/Users/hansmathiasmamenvege/Programming/LQCD/"
"LatticeAnalyser"), json_file)
slurm_output_folder = check_relative_path("../data/scaling_output")
slurm_json_output_path = os.path.split(datapath)[0]
slurm_json_output_path = os.path.join(slurm_json_output_path,
"slurm_output_data.json")
# Comment this out to use old file
if os.path.isfile(slurm_json_output_path):
datapath = slurm_json_output_path
# Extract times from slurm files and put into json file
if not os.path.isfile(datapath):
print "No {} found. Loading slurm data.".format(json_file)
load_slurm_folder(slurm_output_folder, slurm_json_output_path)
datapath = slurm_json_output_path
# Basic figure setup
base_figure_folder = check_relative_path("figures")
base_figure_folder = os.path.join(base_figure_folder, "scaling")
check_folder(base_figure_folder, verbose=verbose)
# Strong scaling folder setup
strong_scaling_figure_folder = os.path.join(base_figure_folder, "strong")
check_folder(strong_scaling_figure_folder, verbose=verbose)
# Weak scaling folder setup
weak_scaling_figure_folder = os.path.join(base_figure_folder, "weak")
check_folder(weak_scaling_figure_folder, verbose=verbose)
default_params = get_default_parameters(data_batch_folder="temp",
include_euclidean_time_obs=False)
# Loads scaling times and splits into weak and strong
with open(datapath, "r") as f:
scaling_times = json.load(f)["runs"]
strong_scaling_times = filter_scalings(scaling_times, "strong_scaling_np")
weak_scaling_times = filter_scalings(scaling_times, "weak_scaling_np")
# Splits strong scaling into gen, io, flow
gen_strong_scaling = filter_scalings(strong_scaling_times, "gen")
io_strong_scaling = filter_scalings(strong_scaling_times, "io")
flow_strong_scaling = filter_scalings(strong_scaling_times, "flow")
# Splits weak scaling into gen, io, flow
gen_weak_scaling = filter_scalings(weak_scaling_times, "gen")
gen_weak_scaling = filter_duplicates(gen_weak_scaling)
io_weak_scaling = filter_scalings(weak_scaling_times, "io")
flow_weak_scaling = filter_scalings(weak_scaling_times, "flow")
# Adds number of processors to strong scaling
gen_strong_scaling = add_numprocs(gen_strong_scaling)
io_strong_scaling = add_numprocs(io_strong_scaling)
flow_strong_scaling = add_numprocs(flow_strong_scaling)
# Adds number of processors to strong scaling
gen_weak_scaling = add_numprocs(gen_weak_scaling)
io_weak_scaling = add_numprocs(io_weak_scaling)
flow_weak_scaling = add_numprocs(flow_weak_scaling)
scalings = [
gen_strong_scaling, io_strong_scaling, flow_strong_scaling,
gen_weak_scaling, io_weak_scaling, flow_weak_scaling
]
times_to_scan = ["update_time", "time"]
times_to_scan = ["time"]
# For speedup and retrieving parallelizability fraction.
min_procs = 8
strong_scaling_list = []
weak_scaling_list = []
for time_type in times_to_scan:
# Loops over scaling values in scalings
for sv in scalings:
x = [i["NP"] for i in sv]
y = [i[time_type] for i in sv]
# Sets up filename and folder name
_scaling = list(set([i["runname"].split("_")[0] for i in sv]))
_sc_part = list(set([i["runname"].split("_")[-1] for i in sv]))
assert len(_scaling) == 1, \
"incorrect sv type list: {}".format(_scaling)
assert len(_sc_part) == 1, \
"incorrect sv part list length: {}".format(_sc_part)
_sc_part = _sc_part[0]
_scaling = _scaling[0]
figure_name = "{}_{}_{}.pdf".format(_scaling, _sc_part, time_type)
if _sc_part != "gen" and time_type == "update_time":
print "Skipping {}".format(figure_name)
continue
# Sets correct figure folder
if _scaling == "strong":
_loc = "upper right"
figure_folder = strong_scaling_figure_folder
elif _scaling == "weak":
_loc = "upper left"
figure_folder = weak_scaling_figure_folder
else:
raise ValueError("Scaling type not recognized for"
" folder: {}".format(_scaling))
if _sc_part == "io":
_label = r"Input/Output"
elif _sc_part == "gen":
_label = r"Configuration generation"
else:
_label = _sc_part.capitalize()
_xlabel = r"$N_p$"
if time_type == "time":
_time_type = _sc_part
if _sc_part == "io":
_ylabel = r"$t_\mathrm{IO}$[s]"
else:
_ylabel = r"$t_\mathrm{%s}$[s]" % _time_type.replace(
"_", r"\ ").capitalize()
# Sets speedup labels
if _sc_part == "io":
_ylabel_speedup = (
r"$t_{\mathrm{IO},N_{p=%s}}/t_{\mathrm{IO},N_p}$"
"[s]" % min_procs)
else:
_tmp = _time_type.replace("_", r"\ ").capitalize()
_ylabel_speedup = (
r"$t_{\mathrm{%s},N_{p=%s}}/t_{\mathrm{%s},N_p}$"
"[s]" % (_tmp, min_procs, _tmp))
_tmp_dict = {
"sc": _sc_part,
"x": np.asarray(x),
"y": np.asarray(y),
"label": _label,
"xlabel": _xlabel,
"ylabel": _ylabel,
"ylabel_speedup": _ylabel_speedup,
"figure_folder": figure_folder,
"figure_name": figure_name,
"loc": _loc,
}
if _scaling == "strong":
strong_scaling_list.append(_tmp_dict)
else:
weak_scaling_list.append(_tmp_dict)
plot_scaling(x,
y,
_label,
_xlabel,
_ylabel,
figure_folder,
figure_name,
loc=_loc)
plot_all_scalings(strong_scaling_list, "strong")
plot_all_scalings(weak_scaling_list, "weak")
plot_speedup(strong_scaling_list, "strong")
