results: algoritm comparison plots and plotting scripts

2025-11-07 14:47:12 +01:00
parent bac7118ba6
commit b84118d944
20 changed files with 234 additions and 0 deletions
--- a/results-and-plotting/python/scripts/plot_alg.py
+++ b/results-and-plotting/python/scripts/plot_alg.py
@@ -0,0 +1,104 @@
+from matplotlib.ticker import FuncFormatter
+import pandas as pd
+import matplotlib.pyplot as plt
+import numpy as np
+from matplotlib.lines import Line2D
+from enum import Enum
+
+
+class columns ():
+    benchmark_type = 'benchmark_type'
+    proc_num = 'proc_num'
+    msg_size_bytes = 'msg_size_bytes'
+    repetitions = 'repetitions'
+    t_min_usec = 't_min_usec'
+    t_max_usec = 't_max_usec'
+    t_avg_usec = 't_avg_usec'
+    mpi_datatype = 'mpi_datatype'
+    mpi_red_datatype = 'mpi_red_datatype'
+    mpi_red_op = 'mpi_red_op'
+    creation_time = 'creation_time'
+    n_nodes = 'n_nodes'
+    off_cache_flag = 'off_cache_flag'
+    algorithm = 'algorithm'
+
+
+class collectives(Enum):
+    Bcast = 'Bcast'
+    Reduce = 'Reduce'
+    Allreduce = 'Allreduce'
+    Alltoall = 'Alltoall'
+    Scatter = 'Scatter'
+    Reduce_scatter = 'Reduce_scatter'
+    Allgather = 'Allgather'
+    Gather = 'Gather'
+
+
+data_file = "./data/data_04_11_25_algs.csv"
+
+df_multinode = pd.read_csv(data_file, delimiter=',')
+df_multinode.fillna(0, inplace=True)
+df_multinode = df_multinode[df_multinode[columns.off_cache_flag] == 50]
+for c in collectives:
+
+    df_single = df_multinode[df_multinode[columns.benchmark_type]
+                             == c.value]
+    df_single = df_single[df_single[columns.msg_size_bytes] > 1000]
+    df_single = df_single[[columns.proc_num, columns.msg_size_bytes,
+                           columns.t_avg_usec, columns.algorithm]]
+
+    df_gather_best = df_single.loc[  # pyright: ignore
+        df_single.groupby([columns.msg_size_bytes, columns.proc_num])[  # pyright: ignore
+            columns.t_avg_usec].idxmin()
+    ].reset_index(drop=True)
+
+    df_gather_best = df_gather_best[df_gather_best[columns.msg_size_bytes] > 2**17]
+
+    pivot_best = df_gather_best.pivot(index=columns.msg_size_bytes,  # pyright: ignore
+                                      columns=columns.proc_num, values=columns.t_avg_usec)
+
+    X = pivot_best.columns.values   # proc_num
+    Y = pivot_best.index.values     # msg_size_bytes
+    X, Y = np.meshgrid(X, Y)   # pyright: ignore
+    Z = pivot_best.values
+
+    alg_pivot = df_gather_best.pivot(
+        index=columns.msg_size_bytes,
+        columns=columns.proc_num,
+        values=columns.algorithm
+    )
+
+    algorithms = alg_pivot.values.flatten()
+    unique_algs = sorted(pd.unique(algorithms[~pd.isna(algorithms)]))
+    color_map = {alg: i for i, alg in enumerate(unique_algs)}
+    color_values = np.array([color_map.get(a, np.nan) for a in algorithms])
+
+    fig = plt.figure(figsize=(16, 9))
+    ax = fig.add_subplot(111, projection='3d')
+    surf = ax.plot_wireframe(X, Y, Z,
+                             color='black', linewidths=1)
+    surf_points = ax.scatter(X,
+                             Y, Z, c=color_values, cmap='viridis', s=20, depthshade=False)  # pyright: ignore
+
+    handles = [
+        Line2D([0], [0],
+               marker='o', color='w',
+               label=alg,
+               markerfacecolor=plt.cm.viridis(
+                   color_map[alg] / max(len(unique_algs)-1, 1)),
+               markersize=8)
+        for alg in unique_algs
+    ]
+
+    ax.legend(handles=handles, title="Algorithm", loc='upper right')
+    ax.set_xlabel("Process Count")
+    ax.set_ylabel("Message Size [B]")
+    ax.set_zlabel("Average Time [μs]")
+    ax.set_title(f"{c.value}")
+    ax.set_xticks(pivot_best.columns.values)  # pyright: ignore
+    ax.set_xticklabels(pivot_best.columns.values)
+    ax.set_yticks(Y[:, 0])
+    ymin, ymax = ax.get_ylim()
+    ax.set_ylim(ymin*0.8, ymax)   # 30% more space at top
+    ax.set_yticklabels([f"$2^{{{int(np.log2(v))}}}$" for v in Y[:, 0]])
+    plt.savefig(f"./plots/{c.value.lower()}_algcomp.png")