Python2.7 on Ubuntu 14, running a single script fills out the cores

Asked Jun 23 '16 at 17:29

Active Jun 23 '16 at 17:29

Viewed 27 times

I'm not using any parallelization in my code, but when I run my script my cores are all filled. Using htop I can see that all my cores are at 100%; on each core, most of it is red (kernel threads) and about 10% is green. I can also see in the process list my python command repeated about 20 times.

Is it possible Python does some parallelization on its own?

Thanks.

asked Jun 23 '16 at 17:29

yoki

1,796
4
16
27

Is the script one you wrote yourself in its entirety? Are you calling any packages? – nbryans Jun 23 '16 at 17:31
I'm using numpy for calculations. – yoki Jun 23 '16 at 17:32
1

See [this](http://stackoverflow.com/questions/17053671/python-how-do-you-stop-numpy-from-multithreading). It appears that numpy matrix operations may parallelize by default. – nbryans Jun 23 '16 at 17:34
Thank you! Will numpy also automatically use GPUs if I have them? – yoki Jun 23 '16 at 17:36
1

I doubt it, but really I have no idea. – nbryans Jun 23 '16 at 17:37
1

gnumpy is used for GPU calculations. – ahajib Jun 23 '16 at 17:44

Python2.7 on Ubuntu 14, running a single script fills out the cores

0 Answers0