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

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

from common import calc_throughput, load_time_mesurements, get_task_count

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 = []

data_avg = {}

# 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 get_timing(file_path):
    divisor = get_task_count(file_path)
    return [ x / divisor for x in load_time_mesurements(file_path)]


# 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, config, dst_node):
    size = 1024*1024*1024

    if config not in data_avg:
        data_avg[config] = 0

    timing = get_timing(file_path)
    run_idx = 0
    for t in timing:
        tp = calc_throughput(size, t)
        data_avg[config] += tp / len(timing)
        data.append({ runid : run_idx, x_label : dst_node, y_label : tp})
        run_idx = run_idx + 1


def plot_bar(table,node_config,display_x,display_y):
    plt.figure(figsize=(2, 3))

    sns.barplot(x=x_label, y=y_label, data=table, palette="mako", errorbar="sd")

    plt.ylim(0, 75)
    plt.xlabel(display_x)
    plt.ylabel(display_y)

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

def PlotAndrePeakResults():
    data_peakbench_andre = [
        { runid : 0, x_label : 8, y_label : 64 },
        { runid : 0, x_label : 11, y_label : 63 },
        { runid : 0, x_label : 12, y_label : 40 },
        { runid : 0, x_label : 15, y_label : 54 }
    ]

    df = pd.DataFrame(data_peakbench_andre)
    df.set_index(index, inplace=True)
    plot_bar(df, "andrepeak", x_label, y_label)

    return df

# 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):
    dst_nodes = {8,11,12,15}

    for dst_node in dst_nodes:
        file = os.path.join(result_path, f"copy-n0ton{dst_node}-1gib-{node_config}.json")
        process_file_to_dataset(file, node_config, dst_node)

    data_avg[node_config] = data_avg[node_config] / len(dst_nodes)

    df = pd.DataFrame(data)

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

    plot_bar(df, node_config, x_label, y_label)

    return df


def get_scaling_factor(baseline,topline,utilfactor):
    return (topline / baseline) * (1 / utilfactor)


if __name__ == "__main__":
    dsa_df1 = main("1dsa")
    dsa_df2 = main("2dsa")
    dsa_df4 = main("4dsa")
    dsa_df8 = main("8dsa")
    cpu_df8 = main("8cpu")
    cpu_dfandre = PlotAndrePeakResults()

    x_dsacount = "Count of DSAs"
    y_avgtp = "Average Throughput in GiB/s"
    y_scaling = "Scaling Factor"

    data_average = [
        { runid : 0, x_label : 1, y_label : data_avg["1dsa"] },
        { runid : 0, x_label : 2, y_label : data_avg["2dsa"] },
        { runid : 0, x_label : 4, y_label : data_avg["4dsa"] },
        { runid : 0, x_label : 8, y_label : data_avg["8dsa"] }
    ]

    average_df = pd.DataFrame(data_average)
    average_df.set_index(index, inplace=True)

    plot_bar(average_df, "average", x_dsacount, y_avgtp)

    data_scaling = [
        { x_dsacount : 1, y_scaling : get_scaling_factor(data_avg["1dsa"], data_avg["1dsa"], 1) },
        { x_dsacount : 2, y_scaling : get_scaling_factor(data_avg["1dsa"], data_avg["2dsa"], 2) },
        { x_dsacount : 4, y_scaling : get_scaling_factor(data_avg["1dsa"], data_avg["4dsa"], 4) },
        { x_dsacount : 8, y_scaling : get_scaling_factor(data_avg["1dsa"], data_avg["8dsa"], 8) }
    ]

    scaling_df = pd.DataFrame(data_scaling)
    sns.lineplot(x=x_dsacount, y=y_scaling, data=scaling_df, marker='o', linestyle='-', color='b', markersize=8)

    plt.xlim(0,10)
    plt.ylim(0,1.25)
    plt.savefig(os.path.join(output_path, f"plot-dsa-throughput-scaling.pdf"), bbox_inches='tight')
    plt.show()