Benchmark results

Note

The results shown here are based on a simple row by row calculation. This may or may not be ideal though. best performance depends on various factors, such as input size of the arrays to be computed, number of cores available memory bandwith and overall system load. To achieve the best possible results, the chunk size should be carefully chosen.

view_names = ["base", "slight01", "medium01"]
host_name = "NUC"
engine_names = ["naive", "mp-naive", "mp-numpy", "cf-tp-naive", "cf-pp-naive", "cf-tp-numpy", "cf-pp-numpy", "torch"]

Show code cell source Hide code cell source

from pathlib import Path
import json

import ipywidgets as ipw
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd

sns.set()
plt.rcParams['figure.dpi'] = 300

results_dir = Path("/Users/jneines/development/pycon_berlin_2023/mandelbrot/results/")

results = []
for results_file in results_dir.glob("*/*/*.json"):
    with results_file.open("r") as fd:
        result = json.loads(fd.read())
        results.append(result)
        
df = pd.DataFrame(results)

dfs = df[
    (df["view"].isin(view_names))
    & (df["hostname"] == host_name)
    & (df["engine"].isin(engine_names))
].reset_index(drop=True)
print(f"We have {len(dfs)} results to analyze.")

tabs = ipw.Tab()

tabs_children = []
tab_names = []
for view_name, _dfs in dfs.groupby("view"):
    tab_names.append(view_name)
    with plt.ioff():
        output = ipw.Output()
        with output:
            fig, axes = plt.subplots()
            sns.violinplot(data=_dfs, x="engine", y="calculation_time", order=engine_names, ax=axes)
            axes.set_ylim(0, None)
            axes.set_ylabel("Calculation time [s]")
            axes.set_xlabel(None)

            axes.set_xticklabels(["\n" * (x_position%2) + label.get_text() for x_position, label in enumerate(axes.get_xticklabels())])
            axes.set_title(view_name)

            plt.tight_layout()
            plt.show()
        tabs_children.append(output)
        
tabs.children = tabs_children
for index, tab_name in enumerate(tab_names):
    tabs.set_title(index, tab_name)

tabs

We have 240 results to analyze.