import os
import json
import pandas as pd
from itertools import chain
import seaborn as sns
import matplotlib.pyplot as plt

from common import calc_throughput

runid = "Run ID"
x_label = "Destination Node"
y_label = "Source Node"
v_label = "Throughput"

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"""

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 load_time_mesurements(file_path):
    with open(file_path, 'r') as file:
        data = json.load(file)
        count = data["count"]
        batch_size = data["list"][0]["task"]["batching"]["batch_size"] if data["list"][0]["task"]["batching"]["batch_size"] > 0 else 1
        iterations = data["list"][0]["task"]["iterations"]

        return {
            "total": sum([x / (iterations * batch_size * count * count) for x in list(chain([data["list"][i]["report"]["time"]["total"] for i in range(count)]))]),
            "combined": [ x / (count * batch_size) for x in list(chain(*[data["list"][i]["report"]["time"]["combined"] for i in range(count)]))],
            "submission": [ x / (count * batch_size) for x in list(chain(*[data["list"][i]["report"]["time"]["submission"] for i in range(count)]))],
            "completion": [ x / (count * batch_size) for x in list(chain(*[data["list"][i]["report"]["time"]["completion"] for i in range(count)]))]
        }


# 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):
    data_size = 1024*1024*1024

    try:
        time = [load_time_mesurements(file_path)["total"]]
        run_idx = 0
        for t in time:
            data.append({ runid : run_idx, x_label : dst_node, y_label : src_node, v_label: calc_throughput(data_size, t)})
            run_idx = run_idx + 1
    except FileNotFoundError:
        return


# 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):
    folder_path = "benchmark-results/"

    for src_node in range(16):
        for dst_node in range(16):
            file = os.path.join(folder_path, f"copy-n{src_node}ton{dst_node}-1gib-{node_config}-1e.json")
            process_file_to_dataset(file, src_node, dst_node)

    df = pd.DataFrame(data)

    data.clear()
    df.set_index(index, inplace=True)
    data_pivot = df.pivot_table(index=y_label, columns=x_label, values=v_label)
    plt.figure(figsize=(8, 6))

    sns.heatmap(data_pivot, annot=True, cmap="rocket_r", fmt=".0f")

    plt.title(title)
    plt.savefig(os.path.join(folder_path, f"plot-perf-{node_config}-throughput.png"), bbox_inches='tight')
    plt.show()


if __name__ == "__main__":
    main("allnodes", title_allnodes)
    main("smart", title_smartnodes)