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

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

runid = "Run ID"
x_label = "Destination Node"
y_label = "Source Node"
v_label = "Throughput"
title = "Copy Throughput for 1GiB Elements running on SRC Node"

index = [ runid, x_label, y_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):
    with open(file_path, 'r') as file:
        data = json.load(file)
        count = data["count"]
        batch_size = 8
        iterations = data["list"][0]["task"]["iterations"]

        return {
            "total": sum([x / (iterations * batch_size * count) for x in list(chain([data["list"][i]["report"]["time"]["total"] for i in range(count)]))]),
            "combined": [ x / (count * batch_size) for x in list(chain(*[data["list"][i]["report"]["time"]["combined"] for i in range(count)]))],
            "submission": [ x / (count * batch_size) for x in list(chain(*[data["list"][i]["report"]["time"]["submission"] for i in range(count)]))],
            "completion": [ x / (count * batch_size) for x in list(chain(*[data["list"][i]["report"]["time"]["completion"] for i in range(count)]))]
        }


def process_file_to_dataset(file_path, src_node, dst_node):
    data_size = 1024*1024*1024

    try:
        time = [load_time_mesurements(file_path)["total"]]
        run_idx = 0
        for t in time:
            data.append({ runid : run_idx, x_label : dst_node, y_label : src_node, v_label: calc_throughput(data_size, t)})
            run_idx = run_idx + 1
    except FileNotFoundError:
        return


def main():
    folder_path = "benchmark-results/"

    for src_node in range(16):
        for dst_node in range(16):
            file = os.path .join(folder_path, f"copy-n{src_node}ton{dst_node}-1gib-4e.json")
            process_file_to_dataset(file, src_node, dst_node)

    df = pd.DataFrame(data)
    df.set_index(index, inplace=True)
    data_pivot = df.pivot_table(index=y_label, columns=x_label, values=v_label)

    sns.heatmap(data_pivot, annot=True, cmap="YlGn", fmt=".0f")

    plt.title(title)
    plt.savefig(os.path.join(folder_path, "plot-perf-peakthroughput.png"), bbox_inches='tight')
    plt.show()


if __name__ == "__main__":
    main()