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

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

runid = "Run ID"
x_label = "Copy Type"
y_label = "Throughput in GiB/s"
var_label = "Configuration"
types = ["intersock-n0ton4-1mib", "internode-n0ton1-1mib", "intersock-n0ton4-1gib", "internode-n0ton1-1gib"]
types_nice = ["Inter-Socket Copy 1MiB", "Inter-Node Copy 1MiB", "Inter-Socket Copy 1GiB", "Inter-Node Copy 1GiB"]
copy_methods = ["dstcopy", "srccopy", "xcopy", "srcoutsidercopy", "dstoutsidercopy", "sockoutsidercopy", "nodeoutsidercopy"]
copy_methods_nice = [ "Engine on DST-Node", "Engine on SRC-Node", "Cross-Copy / Both Engines", "Engine on SRC-Socket, not SRC-Node", "Engine on DST-Socket, not DST-Node", "Engine on different Socket", "Engine on same Socket but neither SRC nor DST Node"]
title = "Performance of Engine Location - Copy Operation on DDR with 1 Engine per WQ"

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_copy_json(file_path,method_label):
    with open(file_path, 'r') as file:
        data = json.load(file)
        iterations = data["list"][0]["task"]["iterations"]
        
        # Extracting time from JSON structure
        if method_label == "xcopy":
            # For xcopy method, add times from two entries and divide by 3
            time0 = data["list"][0]["report"]["time"]
            time1 = data["list"][1]["report"]["time"]

            return {
                "total": max(time0["total"],time1["total"]),
                "combined" : [max(x,y) for x,y in zip(time0["combined"], time1["combined"])],
                "submission" : [max(x,y) for x,y in zip(time0["completion"], time1["completion"])],
                "completion" : [max(x,y) for x,y in zip(time0["submission"], time1["submission"])]
            }

        else:
            return data["list"][0]["report"]["time"]

# Function to plot the graph for the new benchmark
def create_copy_dataset(file_path, method_label, type_label):
    method_index = index_from_element(method_label,copy_methods)
    method_nice = copy_methods_nice[method_index]
    type_index = index_from_element(type_label, types)
    type_nice = types_nice[type_index]
    data_size = 0

    if type_label in ["internode-n0ton1-1mib", "intersock-n0ton4-1mib"]:
        data_size = 1024 * 1024
    else:
        data_size = 1024*1024*1024

    try:
        time = load_and_process_copy_json(file_path,method_label)["total"]
        run_idx = 0
        for t in time:
            data.append({ runid : run_idx, x_label: type_nice, var_label : method_nice, y_label : calc_throughput(data_size, t)})
            run_idx = run_idx + 1
    except FileNotFoundError:
        return

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

    for method_label in copy_methods:
        for type_label in types:
            file = os.path.join(folder_path, f"{method_label}-{type_label}-1e.json")
            create_copy_dataset(file, method_label, 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-enginelocation.png"), bbox_inches='tight')
    plt.show()

if __name__ == "__main__":
    main()