bachelor-thesis/benchmarks/benchmark-plotters/plot-cost-mtsubmit.py

import os
import json
import pandas as pd
from pandas.core.ops import methods
import seaborn as sns
import matplotlib.pyplot as plt

x_label = "Copy Type"
y_label = "Throughput in GiB/s"
var_label = "Thread Counts"
thread_counts = ["1t", "2t", "4t", "8t", "12t"]
thread_counts_nice = ["1 Thread", "2 Threads", "4 Threads", "8 Threads", "12 Threads"]
engine_counts = ["1e", "4e"]
engine_counts_nice = ["1 Engine per Group", "4 Engines per Group"]
title = "Performance of Multi-Threaded Submit - Copy Operation Intra-Node on DDR with Size 1 MiB"

data = {
    x_label : thread_counts_nice,
    engine_counts_nice[0] : [],
    engine_counts_nice[1] : [],
}


def calc_throughput(size_bytes,time_microseconds):
    time_seconds = time_microseconds * 1e-6
    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


# Function to load and process the JSON file for the multi-threaded benchmark
def load_and_process_mt_json(file_path):
    with open(file_path, 'r') as file:
        data = json.load(file)

        # Extracting count from JSON structure
        count = data["count"]

        # Extracting time from JSON structure for elements 0 to count
        times = [data["list"][i]["report"]["time"]["combined_avg"] for i in range(count)]

        # Calculating the average of times
        average_time = sum(times) / count

        return average_time


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

    for file_path in file_paths:
        # Load and process JSON file for the new benchmark
        time_microseconds = load_and_process_mt_json(file_path)
        times.append(time_microseconds)

    engine_index = index_from_element(engine_label,engine_counts)
    engine_nice = engine_counts_nice[engine_index]

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

    data[engine_nice] = throughput


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

    for engine_label in engine_counts:
        mt_file_paths = [os.path.join(folder_path, f"mtsubmit-{thread_count}-{engine_label}.json") for thread_count in thread_counts]
        plot_mt_graph(mt_file_paths, engine_label)

    df = pd.DataFrame(data)
    dfm = pd.melt(df, id_vars=x_label, var_name=var_label, value_name=y_label)

    sns.catplot(x=x_label, y=y_label, hue=var_label, data=dfm, kind='bar', height=5, aspect=1, palette="viridis")
    plt.title(title)
    plt.savefig(os.path.join(folder_path, "plot-cost-mtsubmit.png"), bbox_inches='tight')
    plt.show()

if __name__ == "__main__":
    main()