Skip to content

MNT use new threadpoolctl API (global threadpool controller) #21206

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 10 commits into from
Oct 8, 2021
Merged

MNT use new threadpoolctl API (global threadpool controller) #21206

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
a0d0b53
wip
jeremiedbb Sep 29, 2021
9a6e2d2
wip
jeremiedbb Sep 29, 2021
87c3fef
helper to use the new threadpoolctl API when possible
jeremiedbb Sep 30, 2021
b571590
cln
jeremiedbb Sep 30, 2021
6cc66f2
cln
jeremiedbb Sep 30, 2021
69ccc30
cln
jeremiedbb Sep 30, 2021
26ab63d
cln
jeremiedbb Sep 30, 2021
e0a7b1f
change logic, lazy creation of the controller
jeremiedbb Oct 1, 2021
d1b68ef
Merge branch 'master' into global-threadpool-controller
jeremiedbb Oct 1, 2021
3b8fc79
use it the code base
jeremiedbb Oct 4, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions sklearn/cluster/_kmeans.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,13 +15,13 @@

import numpy as np
import scipy.sparse as sp
from threadpoolctl import threadpool_limits
from threadpoolctl import threadpool_info

from ..base import BaseEstimator, ClusterMixin, TransformerMixin
from ..metrics.pairwise import euclidean_distances
from ..metrics.pairwise import _euclidean_distances
from ..utils.extmath import row_norms, stable_cumsum
from ..utils.fixes import threadpool_limits
from ..utils.fixes import threadpool_info
from ..utils.sparsefuncs_fast import assign_rows_csr
from ..utils.sparsefuncs import mean_variance_axis
from ..utils import check_array
Expand Down
2 changes: 1 addition & 1 deletion sklearn/cluster/tests/test_k_means.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,13 +4,13 @@

import numpy as np
from scipy import sparse as sp
from threadpoolctl import threadpool_limits

import pytest

from sklearn.utils._testing import assert_array_equal
from sklearn.utils._testing import assert_allclose
from sklearn.utils.fixes import _astype_copy_false
from sklearn.utils.fixes import threadpool_limits
from sklearn.base import clone
from sklearn.exceptions import ConvergenceWarning

Expand Down
32 changes: 32 additions & 0 deletions sklearn/utils/fixes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,11 +13,13 @@
from functools import update_wrapper
import functools

import sklearn
import numpy as np
import scipy.sparse as sp
import scipy
import scipy.stats
from scipy.sparse.linalg import lsqr as sparse_lsqr # noqa
import threadpoolctl
from .._config import config_context, get_config
from ..externals._packaging.version import parse as parse_version

Expand Down Expand Up @@ -271,3 +273,33 @@ def linspace(start, stop, num=50, endpoint=True, retstep=False, dtype=None, axis
dtype=dtype,
axis=axis,
)


# compatibility fix for threadpoolctl >= 3.0.0
# since version 3 it's possible to setup a global threadpool controller to avoid
# looping through all loaded shared libraries each time.
# the global controller is created during the first call to threadpoolctl.
def _get_threadpool_controller():
if not hasattr(threadpoolctl, "ThreadpoolController"):
return None

if not hasattr(sklearn, "_sklearn_threadpool_controller"):
sklearn._sklearn_threadpool_controller = threadpoolctl.ThreadpoolController()

return sklearn._sklearn_threadpool_controller


def threadpool_limits(limits=None, user_api=None):
controller = _get_threadpool_controller()
if controller is not None:
return controller.limit(limits=limits, user_api=user_api)
else:
return threadpoolctl.threadpool_limits(limits=limits, user_api=user_api)


def threadpool_info():
controller = _get_threadpool_controller()
if controller is not None:
return controller.info()
else:
return threadpoolctl.threadpool_info()