fix larger than memory error

exercises/exerciseC/plot.py

@@ -3,11 +3,11 @@ import numpy as np
 import matplotlib.pyplot as plt
 import matplotlib.patheffects as PathEffects
 
-N_processes = 5
-N_threads = 5
+N_processes = 16
+N_threads = 16
 
 # Load measured timings
-times = np.empty((N_processes, N_threads))
+times = np.ones((N_processes, N_threads))
 for fname in os.listdir('timings'):
     values = open(f'timings/{fname}').read().split()
     n_processes = int(values[0])
@@ -25,6 +25,7 @@ fig_time.colorbar(im, ax=axs_time, label='Measured computation time (s)')
 """ Plot speedup """
 workers = np.arange(N_processes + 1)[:, None] * np.arange(N_threads + 1)
 speedup = times[0, 0] / times
+speedup[times == 0] = np.nan
 
 fig_speedup, axs_speedup = plt.subplots()
 im = axs_speedup.imshow(speedup.T, origin='lower')
@@ -36,13 +37,13 @@ for axs, data in zip([axs_time, axs_speedup], [times, speedup]):
     axs.set_xlabel('# processes')
     axs.set_ylabel('# threads')
     axs.set_xticks(np.arange(N_processes))
-    axs.set_xticklabels(np.arange(N_processes)+1)
+    axs.set_xticklabels(np.arange(N_processes)+1, fontsize=6)
     axs.set_yticks(np.arange(N_threads))
-    axs.set_yticklabels(np.arange(N_threads)+1)
+    axs.set_yticklabels(np.arange(N_threads)+1, fontsize=6)
 
     for i in range(N_processes):
         for j in range(N_threads):
-            txt = axs.text(i, j, f'{data[i, j]:.2f}', fontsize=10, color='w',
+            txt = axs.text(i, j, f'{data[i, j]:.2f}', fontsize=4, color='w',
                         ha='center', va='center', fontweight='bold')
             txt.set_path_effects([PathEffects.withStroke(linewidth=0.5, foreground='k')])
     axs.spines[['right', 'top']].set_visible(False)

exercises/exerciseC/process_images.py

@@ -6,9 +6,12 @@ import time
 def process_image(input_tuple):
 
     fname, A = input_tuple
+    if len(A.shape) > 2:
+        A = A.mean(axis=-1)  # Take average color
+    A = A[::5, ::5]  # Downsample
     n_threads = os.getenv('OMP_NUM_THREADS', '(unset)')
     print(f"Worker {fname=} OMP_NUM_THREADS={n_threads}", flush=True)
-
+    
     # Decompose image
     U, S, Vh = np.linalg.svd(A)
 
@@ -57,10 +60,10 @@ if __name__ == '__main__':
         new_images = p.map(process_image, image_arrays)
     elapsed_time = time.time() - start_time
 
-    # I/O save the processed images
-    for im, fname in zip(new_images, fnames):
-        im = Image.fromarray(im)
-        im.save(fname.replace('images', 'processed_images'))
+    # # I/O save the processed images
+    # for im, fname in zip(new_images, fnames):
+    #     im = Image.fromarray(im)
+    #     im.save(fname.replace('images', 'processed_images'))
 
     print(f'{n_processes} processes and {n_threads} threads and {len(fnames)} jobs: {elapsed_time}\n',
           flush=True)

exercises/exerciseC/run_with_all_configurations.sh

@@ -1,8 +1,8 @@
 # This is bash
 # It runs the python script multiple times with different arguments
-for i in {1..5}  # Number of processes
+for i in {1..16}  # Number of processes
 do
-    for j in {1..5}  # Number of threads
+    for j in {1..16}  # Number of threads
     do
         python process_images.py $i $j images/*
     done