These are chat archives for ipython/ipython
python, too, not just
python. Definitely should have checked that first. I'll try to narrow it down more.
nomklversions already. They're actually faster.
import mkl; mkl.set_num_threads(1)from Python.
np.linalg.bench('full'), for example, nicely only occupies a single core.
htopbehaves differently on the two machines (although I made sure the settings were equal - outdated package maybe?)
Here is some more information: I am using OpenBlas, but it turns out that
numpy.dot is the evil function. So it is similar to the MKL problem, just with OpenBlas. The solution was to disable automatic parallelisation. I put
export OMP_NUM_THREADS=1 export MKL_NUM_THREADS=1 export NUMEXPR_NUM_THREADS=1