# Theano GPU vs pure Numpy (CPU)

In this benchmark, I’ve used a Windows 10 Pro 64 Bit computer with Intel Core i7 6700HQ 2.60 GHz with 32 Gb RAM and NVIDIA GeForce GTX 960M. As a programming environment, I’ve used Python 2.7 (Anaconda distribution) and Jupyter.

The task is very simple, integrating this expression (simple but effective):

The code I’ve written is this (without matplotlib functions and float32 numbers, in order to use the GPU):

import math from datetime import datetime import numpy as np import matplotlib.pyplot as plt import theano import theano.tensor as T from theano import function, shared # Define constants a = 0 b = math.pi precision = 10000000.0 delta = ((b-a) / precision) # Define x linear space xs = np.linspace(a, b, num=precision).astype(np.float32) # Define Theano function xss = shared(xs, 'xss') deltas = shared(delta, 'delta') sinvx = T.sum(T.sin(xss) * deltas) sf = function([], sinvx) # Number of iterations num_executions = 500 execution_times = [] # Theano test for i in range(num_executions): t0 = datetime.now() res = sf() t1 = datetime.now() execution_times.append((t1-t0).microseconds) et = np.array(execution_times) print ('Theano:') print ('Result: %f' % res) print('Average execution time: %d (us)' % np.average(et)) execution_times = [] # Numpy test for i in range(num_executions): t0 = datetime.now() res = (sin(xs) * delta).sum() t1 = datetime.now() execution_times.append((t1-t0).microseconds) et = np.array(execution_times) print('Numpy:') print('Result: %f' % res) print('Average execution time: %d (us)' % np.average(et))

Final results are:

Using gpu device 0: GeForce GTX 960M (CNMeM is enabled with initial size: 20.0% of memory, CuDNN 3007) Theano: Result: 2.000000 Average execution time: 39690 (us) Numpy: Result: 2.000001 Average execution time: 158240 (us)

So, Numpy is on average 300% slower than Theano (with GPU support). Here the diagrams:

The spikes should be due to CPU overload, multitasking or memory swapping. However, it’s absolutely clear that Theano (I’m going to test also Tensorflow) should be the best choice if you want to implement deep learning algorithms (in particular if you have a good GPU).

See also:

## Machine Learning Algorithms – Giuseppe Bonaccorso

My latest machine learning book has been published and will be available during the last week of July. From the back cover: In this book you will learn all the important Machine Learning algorithms that are commonly used in the field of data science.

## 2 thoughts on “Theano GPU vs pure Numpy (CPU)”

Your example code needs a slight correction. You should clear the execution_times array between the Theano and Numpy runs. As it is, the Theano execution times are included in the Numpy average. Just add a, execution_times = [], after the Theano results are printed and before the Numpy calculations are started.

Best regards,

Jim

Thanks Jim. Indeed it was a typo when copying from the Jupyter notebook. However, the calculations are correct (confirmed also by the plots).