From 59853ffc920f458d04fda524c60131c399d330f1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Constantin=20F=C3=BCrst?= <c@fuersten.info>
Date: Wed, 6 Dec 2023 13:20:22 +0100
Subject: [PATCH] remove the mtsubmit performance plotter which was based on a
 false assumption, modify the mtsubmit cost plotter for the new task set size

---
 .../benchmark-plotters/plot-cost-mtsubmit.py  |  6 +-
 .../benchmark-plotters/plot-perf-mtsubmit.py  | 90 -------------------
 2 files changed, 3 insertions(+), 93 deletions(-)
 delete mode 100644 benchmarks/benchmark-plotters/plot-perf-mtsubmit.py

diff --git a/benchmarks/benchmark-plotters/plot-cost-mtsubmit.py b/benchmarks/benchmark-plotters/plot-cost-mtsubmit.py
index 0e874b5..b368eaa 100644
--- a/benchmarks/benchmark-plotters/plot-cost-mtsubmit.py
+++ b/benchmarks/benchmark-plotters/plot-cost-mtsubmit.py
@@ -13,7 +13,7 @@ thread_counts = ["1t", "2t", "4t", "8t", "12t"]
 thread_counts_nice = ["1 Thread", "2 Threads", "4 Threads", "8 Threads", "12 Threads"]
 engine_counts = ["1e", "4e"]
 engine_counts_nice = ["1 Engine per Group", "4 Engines per Group"]
-title = "Throughput per Thread - Copy Operation Intra-Node on DDR with Size 1 MiB"
+title = "Combined Throughput - Copy Operation Intra-Node on DDR with Size 1 MiB"
 
 index = [runid, x_label, var_label]
 data = []
@@ -57,7 +57,7 @@ def create_mtsubmit_dataset(file_paths, engine_label):
         times.append(time["combined"])
         idx = idx + 1
 
-    throughput = [[calc_throughput(1024*1024,time) for time in t] for t in times]
+    throughput = [[calc_throughput(10*1024*1024,time) for time in t] for t in times]
 
     idx = 0
     for run_set in throughput:
@@ -82,7 +82,7 @@ def main():
     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-cost-mtsubmit.png"), bbox_inches='tight')
+    plt.savefig(os.path.join(folder_path, "plot-perf-mtsubmit.png"), bbox_inches='tight')
     plt.show()
 
 
diff --git a/benchmarks/benchmark-plotters/plot-perf-mtsubmit.py b/benchmarks/benchmark-plotters/plot-perf-mtsubmit.py
deleted file mode 100644
index 610e094..0000000
--- a/benchmarks/benchmark-plotters/plot-perf-mtsubmit.py
+++ /dev/null
@@ -1,90 +0,0 @@
-import os
-import json
-import pandas as pd
-from itertools import chain
-import seaborn as sns
-import matplotlib.pyplot as plt
-
-runid = "Run ID"
-x_label = "Thread Count"
-y_label = "Throughput in GiB/s"
-var_label = "Thread Counts"
-thread_counts = ["1t", "2t", "4t", "8t", "12t"]
-thread_counts_nice = ["1 Thread", "2 Threads", "4 Threads", "8 Threads", "12 Threads"]
-engine_counts = ["1e", "4e"]
-engine_counts_nice = ["1 Engine per Group", "4 Engines per Group"]
-title = "Combined Throughput - Copy Operation Intra-Node on DDR with Size 1 MiB"
-
-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):
-    with open(file_path, 'r') as file:
-        data = json.load(file)
-     
-        count = data["count"]
-
-        return {
-            "combined" : [x / count for x in list(chain(*[data["list"][i]["report"]["time"]["combined"] for i in range(count)]))],
-            "submission" : [x / count for x in list(chain(*[data["list"][i]["report"]["time"]["submission"] for i in range(count)]))],
-            "completion" : [x / count for x in list(chain(*[data["list"][i]["report"]["time"]["completion"] for i in range(count)]))]
-        }
-
-# Function to plot the graph for the new benchmark
-def create_mtsubmit_dataset(file_paths, engine_label):
-    times = []
-
-    engine_index = index_from_element(engine_label,engine_counts)
-    engine_nice = engine_counts_nice[engine_index]
-
-    idx = 0
-    for file_path in file_paths:
-        time = load_and_process_copy_json(file_path)
-        times.append(time["combined"])
-        idx = idx + 1
-
-    throughput = [[calc_throughput(1024*1024,time) for time in t] for t in times]
-
-    idx = 0
-    for run_set in throughput:
-        run_idx = 0
-        for run in run_set:
-            data.append({ runid : run_idx, x_label: thread_counts_nice[idx], var_label : engine_nice, y_label : throughput[idx][run_idx]})
-            run_idx = run_idx + 1
-        idx = idx + 1
-
-
-# Main function to iterate over files and create plots for the new benchmark
-def main():
-    folder_path = "benchmark-results/"  # Replace with the actual path to your folder
-
-    for engine_label in engine_counts:
-        mt_file_paths = [os.path.join(folder_path, f"mtsubmit-{thread_count}-{engine_label}.json") for thread_count in thread_counts]
-        create_mtsubmit_dataset(mt_file_paths, engine_label)
-
-    df = pd.DataFrame(data)
-    df.set_index(index, inplace=True)
-
-    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-mtsubmit.png"), bbox_inches='tight')
-    plt.show()
-
-
-if __name__ == "__main__":
-    main()