You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
100 lines
3.3 KiB
100 lines
3.3 KiB
import os
|
|
import json
|
|
import pandas as pd
|
|
from pandas.core.ops import methods
|
|
from typing import List
|
|
import seaborn as sns
|
|
import matplotlib.pyplot as plt
|
|
|
|
runid = "Run ID"
|
|
x_label = "Size of Submitted Task"
|
|
y_label = "Throughput in GiB/s, LogScale"
|
|
var_label = "Submission Type"
|
|
sizes = ["1kib", "4kib", "1mib", "32mib"]
|
|
sizes_nice = ["1 KiB", "4 KiB", "1 MiB", "32 MiB"]
|
|
types = ["bs10", "bs50", "ms10", "ms50", "ssaw"]
|
|
types_nice = ["Batch, Size 10", "Batch, Size 50", "Multi-Submit, Count 10", "Multi-Submit, Count 50", "Single Submit"]
|
|
title = "Optimal Submission Method - Copy Operation tested Intra-Node on DDR"
|
|
|
|
index = [runid, x_label, var_label]
|
|
data = []
|
|
|
|
def calc_throughput(size_bytes,time_ns):
|
|
time_seconds = time_ns * 1e-9
|
|
size_gib = size_bytes / (1024 ** 3)
|
|
throughput_gibs = size_gib / time_seconds
|
|
return throughput_gibs
|
|
|
|
|
|
def index_from_element(value,array):
|
|
for (idx,val) in enumerate(array):
|
|
if val == value: return idx
|
|
return 0
|
|
|
|
|
|
def load_time_mesurements(file_path,type_label):
|
|
with open(file_path, 'r') as file:
|
|
data = json.load(file)
|
|
iterations = data["list"][0]["task"]["iterations"]
|
|
divisor = 1
|
|
|
|
# bs and ms types for submission process more than one
|
|
# element per run and the results therefore must be
|
|
# divided by this number
|
|
|
|
if type_label in ["bs10", "ms10"]: divisor = 10
|
|
elif type_label in ["ms50", "bs50"]: divisor = 50
|
|
else: divisor = 1
|
|
|
|
return {
|
|
"total": data["list"][0]["report"]["time"]["total"] / (iterations * divisor),
|
|
"combined": [ x / divisor for x in data["list"][0]["report"]["time"]["combined"]],
|
|
"submission": [ x / divisor for x in data["list"][0]["report"]["time"]["submission"]],
|
|
"completion": [ x / divisor for x in data["list"][0]["report"]["time"]["completion"]]
|
|
}
|
|
|
|
|
|
def process_file_to_dataset(file_path, type_label,size_label):
|
|
type_index = index_from_element(type_label,types)
|
|
type_nice = types_nice[type_index]
|
|
size_index = index_from_element(size_label, sizes)
|
|
size_nice = sizes_nice[size_index]
|
|
data_size = 0
|
|
|
|
if size_label == "1kib": data_size = 1024;
|
|
elif size_label == "4kib": data_size = 4 * 1024;
|
|
elif size_label == "1mib": data_size = 1024 * 1024;
|
|
elif size_label == "32mib": data_size = 32 * 1024 * 1024;
|
|
elif size_label == "1gib": data_size = 1024 * 1024 * 1024;
|
|
else: data_size = 0
|
|
|
|
try:
|
|
time = [load_time_mesurements(file_path,type_label)["total"]]
|
|
run_idx = 0
|
|
for t in time:
|
|
data.append({ runid : run_idx, x_label: type_nice, var_label : size_nice, y_label : calc_throughput(data_size, t)})
|
|
run_idx = run_idx + 1
|
|
except FileNotFoundError:
|
|
return
|
|
|
|
|
|
|
|
def main():
|
|
folder_path = "benchmark-results/"
|
|
|
|
for type_label in types:
|
|
for size in sizes:
|
|
file = os.path.join(folder_path, f"submit-{type_label}-{size}-1e.json")
|
|
process_file_to_dataset(file, type_label, size)
|
|
|
|
df = pd.DataFrame(data)
|
|
df.set_index(index, inplace=True)
|
|
df = df.sort_values(y_label)
|
|
|
|
sns.barplot(x=x_label, y=y_label, hue=var_label, data=df, palette="rocket", errorbar="sd")
|
|
plt.title(title)
|
|
plt.savefig(os.path.join(folder_path, "plot-opt-submitmethod.png"), bbox_inches='tight')
|
|
plt.show()
|
|
|
|
if __name__ == "__main__":
|
|
main()
|