bachelor-thesis/benchmarks/benchmark-plotters/plot-perf-submitmethod.py

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"
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 = "Performance of Submission Methods - Copy Operation tested Intra-Node on DDR"

index = [runid, x_label, var_label]
data = []

def calc_throughput(size_bytes,time_microseconds):
    time_seconds = time_microseconds * 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_and_process_submit_json(file_path):
    with open(file_path, 'r') as file:
        data = json.load(file)
        return data["list"][0]["report"]["time"]


# Function to plot the graph for the new benchmark
def create_submit_dataset(file_paths, type_label):
    times = []

    type_index = index_from_element(type_label,types)
    type_nice = types_nice[type_index]

    idx = 0
    for file_path in file_paths:
        time = load_and_process_submit_json(file_path)
        times.append(time["combined"])
        idx = idx + 1

    # Adjust time measurements based on type
    # which can contain multiple submissions
    if type_label in {"bs10", "ms10"}:
        times = [[t / 10  for t in time] for time in times]
    elif type_label in {"ms50", "bs50"}:
        times = [[t / 50  for t in time] for time in times]

    times[0] = [t / 1 for t in times[0]]
    times[1] = [t / 4 for t in times[1]]
    times[2] = [t / (1024) for t in times[2]]
    times[3] = [t / (32*1024) for t in times[3]]

    throughput = [[calc_throughput(1024,time) for time in t] for t in times]

    idx = 0
    for run_set in throughput:
        run_idx = 0
        for run in run_set:
            data.append({ runid : run_idx, x_label: sizes_nice[idx], var_label : type_nice, y_label : throughput[idx][run_idx]})
            run_idx = run_idx + 1
        idx = idx + 1


# Main function to iterate over files and create plots for the new benchmark
def main():
    folder_path = "benchmark-results/"  # Replace with the actual path to your folder

    for type_label in types:
        file_paths = [os.path.join(folder_path, f"submit-{type_label}-{size}-1e.json") for size in sizes]
        create_submit_dataset(file_paths, type_label)

    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-perf-submitmethod.png"), bbox_inches='tight')
    plt.show()

if __name__ == "__main__":
    main()