Re:Scaling NumPy on Free-Threaded Python
by ngoldbaum on Thursday August 06, 2026 @07:14AM
(#49195178)
There’s also the fact that INCREF and DECREF on shared objects is a lot more expensive than plain integer addition, so stuff becomes a bottleneck that was never a bottleneck. Kumar also fixed a bottleneck caused by a lock added only for safety on the free-threaded build. It’s hard to tell in advance than a fancy lock-free data structure is needed for something.
Re:Scaling NumPy on Free-Threaded Python
by quietbritishjim on Friday August 07, 2026 @08:09AM
(#49209179)
You're talking about the same thing as the article: why were things not as fast as they could be in free threaded mode?
But this comment thread is more of a meta discussion: if numpy already released the GIL, why would lock contention issues only show up now in free threaded mode? That's what I answered above (i.e. yes the GIL was sometimes released by numpy, but there operations really were happening with the GIL locked in non free threaded build).
Re:Scaling NumPy on Free-Threaded Python
by ngoldbaum on Friday August 07, 2026 @09:07AM
(#49209835)
I’m saying that it’s a new issue on the free-threaded build.
Re:Scaling NumPy on Free-Threaded Python
by quietbritishjim on Friday August 07, 2026 @09:16AM
(#49209933)
Right. The original commenter already seemed to understand that.
It's a new issue because the reference count needs locking, whereas previously it didn't because it was implicitly synchronised due to the GIL being locked.
But the original commenter asked: hang on, I thought the GIL wasn't locked for numpy?
Now you have reached the start of the conversation.
Re:Scaling NumPy on Free-Threaded Python
by frollogaston on Thursday August 06, 2026 @09:07AM
(#49196163)
Ah ok, the times I did this and saw full CPU utilization was on pretty large arrays, so there was a lot less time spent in the GIL.
Of course, without free threading, the lock contention would be way worse, but this time the GIL is the lock being contended. Numpy has to reacquire the GIL whenever it returns from a function call, and this expression is made up of multiple calls. To multithread effectively with numpy (in non-freethreading) you'd normally aim to vectorise into a small number of calls in big arrays.
The composition of +, then np.cos, etc. is not too bad if these are big arrays, but the problem is the pure Python iteration over the range which is, presumably, quite large. You could vectorise over the range:
but this is the start of a new conversation.