[PATCH] D153084: AMDGPU: Partially fix not respecting dynamic denormal mode

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added a comment.

In D153084#4474883 <https://reviews.llvm.org/D153084#4474883>, @rampitec wrote:

> Can you please explain why does it need reversal of the HasFP32Denormals? This creates a lot turmoil.

It's conceptually backwards. The default logic has to be treat like IEEE. It needs to be the positive condition that we definitely have flushing on


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D153084/new/

https://reviews.llvm.org/D153084