[PATCH] D139455: AMDGPU: Document denormal behavior

Matt Arsenault via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Mon Feb 20 03:37:39 PST 2023


arsenm added inline comments.


================
Comment at: llvm/docs/AMDGPUUsage.rst:4596
+     by ``"denormal-fp-math"="preserve-sign"``. The behavior is
+     undefined with ``"denormal-fp-math"="positive-zero"``
+
----------------
foad wrote:
> If we can't implement flushing-to-positive-zero then surely we should treat "denormal-fp-math"="positive-zero" the same as "denormal-fp-math"="ieee", since according to LangRef "it is not mandated that flushing to zero occurs" at all. So I don't see where undefined behaviour comes into it.
It's informative of the mode, and we can be a bit lax on the outputs. However, for the input treatment, this acts more like a constraint (e.g. you can't introduce a divide by 0 for a denormal input)


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D139455/new/

https://reviews.llvm.org/D139455



More information about the llvm-commits mailing list