Re:Why SciPy builds for Python 3.12 on Windows are a minor m...
by hurryer on Wednesday November 08, 2023 @06:56PM
(#38198995)
For pure CPU computation Windows is just as fast as Linux since 99.9% of the time it's your code running and not the OS.
[ Parent
| on HN ]
Re:Why SciPy builds for Python 3.12 on Windows are a minor m...
by murderfs on Wednesday November 08, 2023 @07:51PM
(#38199444)
Depending on the code you're running, calling convention can matter a lot. The SysV ABI will use xmm/ymm/zmm automatically, whereas on Windows you have to opt into it with __vectorcall.
Re:Why SciPy builds for Python 3.12 on Windows are a minor m...
by sdfhioandion on Wednesday November 08, 2023 @08:14PM
(#38199644)
Not true. Changes to the OS, particularly to the scheduler, can affect CPU-bound work a great deal. It's "your code", but the OS decides when and where it runs. For example, the changes between Linux 6.5 and Linux 6.6 led to a >20% uplift in TensorFlow and some smaller uplifts to Blender. This is the same software on the same hardware.
https://www.phoronix.com/review/linux66-epyc-xeon/3
I couldn't track down a more detailed scheduler-specific benchmark. I remember reading one on Phoronix a few months back...