Updated Python scripts' logic

plot_3vars.py

@@ -59,7 +59,6 @@ plt.title('Problem Size vs. MFLOP/s')
 plt.xlabel('Problem Size')
 plt.ylabel('MFLOP/s')
 plt.legend()
-plt.savefig('mflops_plot.png')
 
 # Plot Memory Bandwidth Utilization
 plt.figure()
@@ -70,7 +69,6 @@ plt.title('Problem Size vs. Memory Bandwidth Utilization')
 plt.xlabel('Problem Size')
 plt.ylabel('Memory Bandwidth Utilization (%)')
 plt.legend()
-plt.savefig('memory_bandwidth_plot.png')
 
 # Plot Memory Latency
 plt.figure()
@@ -81,6 +79,5 @@ plt.title('Problem Size vs. Memory Latency')
 plt.xlabel('Problem Size')
 plt.ylabel('Memory Latency')
 plt.legend()
-plt.savefig('memory_latency_plot.png')
 
 plt.show()

plot_3vars_savefig.py

@@ -19,51 +19,68 @@ Assumptions: developed and tested using Python version 3.8.8 on macOS 11.6
 import pandas as pd
 import matplotlib.pyplot as plt
 
-plot_fname = "myplot.png"
+# 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="#")
-print(df)
 
-var_names = list(df.columns)
+# 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()
 
-print("var names =", var_names)
+# 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]
 
-# split the df into individual vars
-# assumption: column order - 0=problem size, 1=blas time, 2=basic time
+# 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]
 
-problem_sizes = df[var_names[0]].values.tolist()
-code1_time = df[var_names[1]].values.tolist()
-code2_time = df[var_names[2]].values.tolist()
-code3_time = df[var_names[3]].values.tolist()
+# 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()
+plt.savefig('mflops_plot.png')
 
-plt.title("Comparison of 3 Codes")
-
-xlocs = [i for i in range(len(problem_sizes))]
-
-plt.xticks(xlocs, problem_sizes)
-
-plt.plot(code1_time, "r-o")
-plt.plot(code2_time, "b-x")
-plt.plot(code3_time, "g-^")
-
-#plt.xscale("log")
-#plt.yscale("log")
-
-plt.xlabel("Problem Sizes")
-plt.ylabel("runtime")
-
-varNames = [var_names[1], var_names[2], var_names[3]]
-plt.legend(varNames, loc="best")
-
-plt.grid(axis='both')
-
-# save the figure before trying to show the plot
-plt.savefig(plot_fname, dpi=300)
+# 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()
+plt.savefig('memory_bandwidth_plot.png')
 
+# 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.savefig('memory_latency_plot.png')
 
 plt.show()
-
-# EOF