Tensorflow Cuda GPU vs CPU

tf_GPU_vs_CPU.py

#!/usr/bin/env python3
# coding: utf-8

# Test Cuda availability and benchmark CPU vs GPU
#
# see for example: https://colab.research.google.com/notebooks/gpu.ipynb

import tensorflow as tf
import timeit

device_name = tf.test.gpu_device_name()
# if device_name != '/device:GPU:0':
if not tf.config.list_physical_devices('GPU'):
    raise SystemError('GPU device not found')

print('Found GPU at: {}'.format(device_name))


# Test CPU vs GPU
# 2 functions that calculate random matrices

def cpu():
    with tf.device('/cpu:0'):
        random_image_cpu = tf.random.normal((100, 100, 100, 3))
        net_cpu = tf.keras.layers.Conv2D(32, 7)(random_image_cpu)
        return tf.math.reduce_sum(net_cpu)


def gpu():
    with tf.device('/device:GPU:0'):
        random_image_gpu = tf.random.normal((100, 100, 100, 3))
        net_gpu = tf.keras.layers.Conv2D(32, 7)(random_image_gpu)
        return tf.math.reduce_sum(net_gpu)


# Run each op once to "warm up"; see: https://stackoverflow.com/a/45067900
cpu()
gpu()

# Finally, run the op several times & output formatted result, the latter a matter of taste
print('\nTime (s) to convolve 32x7x7x3 filter over random 100x100x100x3 images '
      '(batch x height x width x channel). \n Sum of ten runs.')

print('CPU (s):', end=" ")
cpu_time = timeit.timeit(stmt=cpu, number=10, setup="from __main__ import cpu")
print("{:.4f}".format(cpu_time))

print('GPU (s):', end=" ")
gpu_time = timeit.timeit(stmt=gpu, number=10, setup="from __main__ import gpu")
print("{:.4f}".format(gpu_time))
print('GPU speedup over CPU: {}x'.format(int(cpu_time / gpu_time)))

'''
comparison outputs
Time (s) to convolve 32x7x7x3 filter over random 100x100x100x3 images (batch x height x width x channel).
Sum of ten runs.

Mx150, win10 (vs i7):
CPU (s): 2.0285
GPU (s): 0.4343
GPU speedup over CPU: 4x

2060S, win10 (vs Ryzen 5 3600):
CPU (s): 0.7966
GPU (s): 0.0775
GPU speedup over CPU: 10x

1050Ti, Ubuntu20 (vs Xeon W3550):
CPU (s): 4.0058:
GPU (s): 0.1734:
GPU speedup over CPU: 23x:

1080Ti, Ubuntu18 (vs Xeon E5 2620 V3):
CPU (s): 0.7239
GPU (s): 0.0535
GPU speedup over CPU: 13x
'''