"""

E. Wes Bethel, Copyright (C) 2022

October 2022

Description: This code loads a .csv file and creates a 3-variable plot

Inputs: the named file "sample_data_3vars.csv"

Outputs: displays a chart with matplotlib

Dependencies: matplotlib, pandas modules

Assumptions: developed and tested using Python version 3.8.8 on macOS 11.6

"""

import pandas as pd
import matplotlib.pyplot as plt

# Constants for calculations
OPS = 1e6  # 1 million operations
BYTES_ACCESSED = 1e9  # Example: 1 GB accessed
PEAK_MEMORY_BANDWIDTH = 100  # Example: 100 GB/s
MEMORY_ACCESSES = 1e6  # Example: 1 million memory accesses

# Read the CSV file
fname = "benchmark_data.csv"
df = pd.read_csv(fname, comment="#")

# Extract columns
problem_sizes = df['Problem Size'].values.tolist()
elapsed_times_direct = df['sum_direct'].values.tolist()
elapsed_times_indirect = df['sum_indirect'].values.tolist()
elapsed_times_vector = df['sum_vector'].values.tolist()

# Calculate MFLOP/s
mflops_direct = [OPS / time for time in elapsed_times_direct]
mflops_indirect = [OPS / time for time in elapsed_times_indirect]
mflops_vector = [OPS / time for time in elapsed_times_vector]

# Calculate Memory Bandwidth Utilization (%)
memory_bandwidth_direct = [(BYTES_ACCESSED / time) / PEAK_MEMORY_BANDWIDTH * 100 for time in elapsed_times_direct]
memory_bandwidth_indirect = [(BYTES_ACCESSED / time) / PEAK_MEMORY_BANDWIDTH * 100 for time in elapsed_times_indirect]
memory_bandwidth_vector = [(BYTES_ACCESSED / time) / PEAK_MEMORY_BANDWIDTH * 100 for time in elapsed_times_vector]

# Calculate Memory Latency
memory_latency_direct = [time / MEMORY_ACCESSES for time in elapsed_times_direct]
memory_latency_indirect = [time / MEMORY_ACCESSES for time in elapsed_times_indirect]
memory_latency_vector = [time / MEMORY_ACCESSES for time in elapsed_times_vector]

# Plot MFLOP/s
plt.figure()
plt.plot(problem_sizes, mflops_direct, label='Direct')
plt.plot(problem_sizes, mflops_indirect, label='Indirect')
plt.plot(problem_sizes, mflops_vector, label='Vector')
plt.title('Problem Size vs. MFLOP/s')
plt.xlabel('Problem Size')
plt.ylabel('MFLOP/s')
plt.legend()

# Plot Memory Bandwidth Utilization
plt.figure()
plt.plot(problem_sizes, memory_bandwidth_direct, label='Direct')
plt.plot(problem_sizes, memory_bandwidth_indirect, label='Indirect')
plt.plot(problem_sizes, memory_bandwidth_vector, label='Vector')
plt.title('Problem Size vs. Memory Bandwidth Utilization')
plt.xlabel('Problem Size')
plt.ylabel('Memory Bandwidth Utilization (%)')
plt.legend()

# Plot Memory Latency
plt.figure()
plt.plot(problem_sizes, memory_latency_direct, label='Direct')
plt.plot(problem_sizes, memory_latency_indirect, label='Indirect')
plt.plot(problem_sizes, memory_latency_vector, label='Vector')
plt.title('Problem Size vs. Memory Latency')
plt.xlabel('Problem Size')
plt.ylabel('Memory Latency')
plt.legend()

plt.show()