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

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

from common import calc_throughput, index_from_element

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 1MiB", "Inter-Node 1MiB", "Inter-Socket 1GiB", "Inter-Node 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"]

title = \
    """Throughput showing impact of Engine Location\n
    Copy Operation on DDR with 1 Engine per WQ"""

description = \
    """Throughput showing impact of Engine Location\n
    Some Configurations missing as they are not feesible\n
    Copy Operation on DDR with 1 Engine per WQ"""

index = [runid, x_label, var_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,method_label):
    with open(file_path, 'r') as file:
        data = json.load(file)
        iterations = data["list"][0]["task"]["iterations"]
        
        if method_label == "xcopy":
            # xcopy runs on two engines that both copy 1/2 of the entire
            # specified size of 1gib, therefore the maximum time between
            # these two is going to be the total time for copy

            time0 = data["list"][0]["report"]["time"]
            time1 = data["list"][1]["report"]["time"]

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

        else:
            return {
                "total": data["list"][0]["report"]["time"]["total"] / iterations,
                "combined": data["list"][0]["report"]["time"]["combined"],
                "submission": data["list"][0]["report"]["time"]["submission"],
                "completion": data["list"][0]["report"]["time"]["completion"]
            }


# 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 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-n0ton1-1gib", "intersock-n0ton4-1gib"]: data_size = 1024*1024*1024
    elif type_label in ["internode-n0ton1-1mib", "intersock-n0ton4-1mib"]: data_size = 1024 * 1024
    else: data_size = 0

    try:
        run_idx = 0
        time = [load_time_mesurements(file_path,method_label)["total"]]
        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


# 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():
    result_path = "benchmark-results/"
    output_path = "benchmark-plots/"

    for method_label in copy_methods:
        for type_label in types:
            file = os.path.join(result_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(output_path, "plot-perf-enginelocation.png"), bbox_inches='tight')
    plt.show()

if __name__ == "__main__":
    main()