[PATCH] D157875: AMDGPU: Replace fabs and copysign libcalls with intrinsics

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec accepted this revision.
rampitec added a comment.
This revision is now accepted and ready to land.

In D157875#4585827 <https://reviews.llvm.org/D157875#4585827>, @arsenm wrote:

> In D157875#4585822 <https://reviews.llvm.org/D157875#4585822>, @rampitec wrote:
>
>> Why does it need strict-fp? Isn't it defined as just a bit operation?
>
> It doesn't, that's why it's allowed here unlike the other cases

Ough, I see. LGTM.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D157875/new/

https://reviews.llvm.org/D157875