Why is my GPU slower than CPU when training LSTM/RNN models?

Question

My machine has the following spec:

CPU: Xeon E5-1620 v4

GPU: Titan X (Pascal)

Ubuntu 16.04

Nvidia driver 375.26

CUDA tookit 8.0

cuDNN 5.1

I've benchmarked on the following Keras examples with Tensorflow as the backed reference:

SCRIPT NAME                  GPU       CPU
stated_lstm.py               5sec      5sec 
babi_rnn.py                  10sec     12sec
imdb_bidirectional_lstm.py   240sec    116sec
imbd_lstm.py                 113sec    106sec

My gpu is clearly out performing my cpu in non-lstm models.

SCRIPT NAME                  GPU       CPU
cifar10_cnn.py               12sec     123sec
imdb_cnn.py                  5sec      119sec
mnist_cnn.py                 3sec      47sec 

Has anyone else experienced this?

Answer 1

This is mainly due to the sequential computation in the LSTM layer. Remember that LSTM requires sequential input to calculate the hidden layer weights iteratively, in other words, you must wait for the hidden state at time t-1 to calculate the hidden state at time t.

That's not a good idea for GPU cores since they are many small cores who like doing computations in parallel, sequential computation can't fully utilize their computing powers. That's why we are seeing GPU load around 10% - 20% most of the time.

But in the phase of backpropagation, GPU could run a derivative computation in parallel, so we can see the GPU load peak around 80%.

For LSTM, check out the Recurrent Neural Network by Intellipaat. This will help in cracking Machine Learning Interview Questions as well for a tech newbie.