This contains my bachelors thesis and associated tex files, code snippets and maybe more. Topic: Data Movement in Heterogeneous Memories with Intel Data Streaming Accelerator
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 

94 lines
3.0 KiB

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 = []
# 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, src_node, dst_node):
size = 1024*1024*1024
timing = get_timing(file_path)
run_idx = 0
for t in timing:
tp = calc_throughput(size, t)
data.append({ runid : run_idx, x_label : dst_node, y_label : tp})
run_idx = run_idx + 1
def plot_bar(table,title,node_config):
plt.figure(figsize=(2, 3))
sns.barplot(x=x_label, y=y_label, data=table, palette="mako", errorbar="sd")
plt.ylim(0, 75)
plt.savefig(os.path.join(output_path, f"plot-{node_config}-cpu-throughput.pdf"), bbox_inches='tight')
plt.show()
# 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,title,ext):
src_node = 0
for dst_node in {8,11,12,15}:
file = os.path.join(result_path, f"copy-n{src_node}ton{dst_node}-1gib-{node_config}{ext}.json")
process_file_to_dataset(file, src_node, dst_node)
df = pd.DataFrame(data)
data.clear()
df.set_index(index, inplace=True)
if ext == "brute": node_config = ext
plot_bar(df, title, node_config)
return df
if __name__ == "__main__":
dall = main("allnodes", title_allnodes, "-cpu")
dbrt = main("brute", title_allnodes, "-cpu")