[PATCH] D108037: [X86] Implement llvm.isnan(x86_fp80) as unordered comparison

[Siva Chandra via Phabricator via llvm-commits]

sivachandra added a comment.

In D108037#2944441 <https://reviews.llvm.org/D108037#2944441>, @efriedma wrote:

> I'm not convinced we care about this, though.  We could probably just say in LangRef that floating-point operations on "unsupported" x86_fp80 values produce poison, and nobody would notice the difference.

Its probably debatable whether one should care about the unsupported numbers. But, the reason for my comment on the original change was because we actually noticed the difference :)

Also, other commonly used floating point libraries like the GNU MPFR library treat the unsupported numbers as NaNs.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D108037/new/

https://reviews.llvm.org/D108037