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

import os
import json
import pandas as pd
from itertools import chain
import seaborn as sns
import matplotlib.pyplot as plt

from common import calc_throughput

result_path = "benchmark-results/"
output_path = "benchmark-plots/"

runid = "Run ID"
x_label = "Destination Node"
y_label = "Throughput in GiB/s"

title_allnodes = \
    """Copy Throughput in GiB/s tested for 1GiB Elements\n
    Using all 8 DSA Chiplets available on the System"""
title_smartnodes = \
    """Copy Throughput in GiB/s tested for 1GiB Elements\n
    Using Cross-Copy for Intersocket and all 4 Chiplets of Socket for Intrasocket"""
title_difference = \
    """Gain in Copy Throughput in GiB/s of All-DSA vs. Smart Assignment"""

description_smartnodes = \
    """Copy Throughput in GiB/s tested for 1GiB Elements\n
    Nodes of {8...15} are HBM accessors for their counterparts (minus 8)\n
    Using all 4 DSA Chiplets of a Socket for Intra-Socket Operation\n
    And using only the Source and Destination Nodes DSA for Inter-Socket"""
description_allnodes = \
    """Copy Throughput in GiB/s tested for 1GiB Elements\n
    Nodes of {8...15} are HBM accessors for their counterparts (minus 8)\n
    Using all 8 DSA Chiplets available on the System"""

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


# loads the measurements from a given file and processes them
# so that they are normalized, meaning that the timings returned
# are nanoseconds per element transfered
def load_time_mesurements(file_path):
    with open(file_path, 'r') as file:
        data = json.load(file)
        count = data["count"]
        batch_size = data["list"][0]["task"]["batching"]["batch_size"] if data["list"][0]["task"]["batching"]["batch_size"] > 0 else 1
        iterations = data["list"][0]["task"]["iterations"]

        return {
            "size": data["list"][0]["task"]["size"],
            "total": sum([x / (iterations * batch_size * count * 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)]))]
        }


# procceses a single file and appends the desired timings
# to the global data-array, handles multiple runs with a runid
# and ignores if the given file is not found as some
# configurations may not be benchmarked
def process_file_to_dataset(file_path, src_node, dst_node):
    try:
        file_data = load_time_mesurements(file_path)
        time = file_data["combined"]
        run_idx = 0
        for t in time:
            data.append({ runid : run_idx, x_label : dst_node, y_label : calc_throughput(file_data["size"], t)})
            run_idx = run_idx + 1
    except FileNotFoundError:
        return


def plot_bar(table,title,node_config):
    plt.figure(figsize=(8, 6))

    sns.barplot(x=x_label, y=y_label, data=table, palette="rocket")

    plt.ylim(0, 100)

    plt.savefig(os.path.join(output_path, f"plot-perf-{node_config}-throughput-selectbarplot.png"), bbox_inches='tight')
    plt.show()


# loops over all possible configuration combinations and calls
# process_file_to_dataset for them in order to build a dataframe
# which is then displayed and saved
def main(node_config,title):
    src_node = 0
    for dst_node in {8,11,12,15}:
        size = "512mib" if node_config == "allnodes" and src_node == dst_node and src_node >= 8 else "1gib" 
        file = os.path.join(result_path, f"copy-n{src_node}ton{dst_node}-{size}-{node_config}-1e.json")
        process_file_to_dataset(file, src_node, dst_node)

    df = pd.DataFrame(data)

    data.clear()
    df.set_index(index, inplace=True)

    plot_bar(df, title, node_config)

    return df


if __name__ == "__main__":
    dall = main("allnodes", title_allnodes)
    dsmart = main("smart", title_smartnodes)