News for hackers. Stuff that matters.
Re:Std: Clamp generates less efficient assembly than std:min... by jcranmer on Tuesday January 16, 2024 @11:12AM (#39014997)
https://github.com/llvm/llvm-project/issues/57589

Turn on fast-math, it flips the FTZ/DAZ bit for the entire application. Even if you turned it on for just a shared library!

Re:Std: Clamp generates less efficient assembly than std:min... by account42 on Wednesday January 17, 2024 @05:02AM (#39025719)
That's only one small part of -ffast-math/-Ofast though and not a very scary one at that.
Re:Std: Clamp generates less efficient assembly than std:min... by mort96 on Wednesday January 17, 2024 @06:39PM (#39035225)
But it's an example of -ffast-math affecting separately compiled libraries.