Amit Dovev

May I ask why do you train with 'lstm1'?

You can make clstm run >x2 faster! https://github.com/tmbdev/clstm/issues/70#issuecomment-310135513

In SConstruct comment this line: `env.Append(CPPDEFINES={'CLSTM_ALL_TENSOR': '1'})`

Tom, So why is a588c8 (matrix only, no tensor) is more than 2.5 faster in training compared to the tip of the repo? Tested on my 4 years old PC,...

I forgot to mention that I tested this with Eigen 3.3 rc1. On Ubuntu 16.04 (gcc ~~5.1~~ 5.4).

I checked with htop. Only one cpu run 100%, the others are idle /

Make sure you are testing cpu only without gpu involvement.

> with the latest code from master I get step times of ~0.3s with the uw3-500 dataset I get ~0.8s with the uw3-500 dataset > while with the a588c8 version...

I can confirm that installing the latest code with `scons debug=-1`, I get the same performance as the matrix based code.

My cpu: ``` model name : Intel(R) Core(TM) i5-3450 CPU @ 3.10GHz stepping : 9 cpu MHz : 2462.683 cache size : 6144 KB cpu cores : 4 ``` gcc...